© 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. 7654
    Prev
    Next
    INDEX
    Explanations

    indents at the start of a line

    oai_token-act-pair · gemini-2.0-flash

    Unstructured identifiers or code terms

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

    Code and comments

    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
    antMatchers
    -0.59
    fetchone
    -0.57
     ExecuteAsync
    -0.52
    bootstrapcdn
    -0.51
    клопе
    -0.50
    endphp
    -0.50
     sho
    -0.50
    <bos>
    -0.49
    carea
    -0.47
     Gaga
    -0.44
    POSITIVE LOGITS
    ConstraintMaker
    0.87
     مشين
    0.83
     للاسماء
    0.74
     وتسجيلات
    0.73
    principalTable
    0.69
     ***!
    0.66
    AnimationsModule
    0.61
    Aiheesta
    0.60
    CrossRef
    0.59
     виправивши
    0.59
    Activations Density 0.356%

    No Known Activations