© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15037
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets, words related to legal documents, some web design terminology, and conversational filler words.

    oai_token-act-pair · gemini-2.0-flash

    the word 'let' in various cases

    np_token-act-pair-logits · gpt-4o-mini

    let

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Tikang
    -0.99
    expandindo
    -0.97
     tartalomajánló
    -0.96
    aarrggbb
    -0.93
     كومونز
    -0.90
    adpleegd
    -0.88
     myſelf
    -0.85
    AutoScaleMode
    -0.85
     мәкал
    -0.82
     autorytatywna
    -0.80
    POSITIVE LOGITS
     let
    3.50
     Let
    2.88
    let
    2.78
    Let
    2.75
     lets
    2.61
     LET
    2.41
     Lets
    2.20
    LET
    2.16
    lets
    2.08
    Lets
    2.08
    Activations Density 4.061%

    No Known Activations