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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6238
    Prev
    Next
    INDEX
    Explanations

    printing and logging statements

    oai_token-act-pair · gemini-2.0-flash

    print statements and debugging outputs in code

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

    code snippets

    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
    клопе
    -0.65
    出し
    -0.60
    Numerology
    -0.58
    estacks
    -0.58
    MenuInflater
    -0.57
     fubject
    -0.57
     Constitucional
    -0.56
    RegressionTest
    -0.56
    GEBURTS
    -0.56
     Bosco
    -0.55
    POSITIVE LOGITS
     doInBackground
    0.49
    #
    0.49
    FormTagHelper
    0.49
    migrationBuilder
    0.45
     ویکی‌پدیای
    0.45
    steamcommunity
    0.45
    Còn
    0.42
    ]='\
    0.41
     }{@
    0.41
     henvis
    0.40
    Activations Density 1.420%

    No Known Activations