© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13332
    Prev
    Next
    INDEX
    Explanations

    words and code snippets from a variety of programming languages and configuration files

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash

    identifiers Method used: 1 — reason: tokens are variable/class/function names from code — explanation: identifiers

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -1.07
    تقاوى
    -1.05
    rungsseite
    -0.99
     nahilalakip
    -0.98
    Autoritní
    -0.97
    MigrationBuilder
    -0.94
     تضيفلها
    -0.94
    AddHtmlAttribute
    -0.93
    
    -0.91
    __*/
    -0.90
    POSITIVE LOGITS
    <bos>
    0.75
     fieldNum
    0.52
     positive
    0.52
    ===========
    0.51
    ulario
    0.50
     Grüße
    0.50
    Искәрмәләр
    0.50
     positivo
    0.49
    됩니다
    0.49
     very
    0.49
    Activations Density 4.114%

    No Known Activations