© 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. 14894
    Prev
    Next
    INDEX
    Explanations

    java documentation links

    oai_token-act-pair · gemini-2.0-flash

    special character sequences

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

    code

    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
    <eos>
    -0.41
    chiat
    -0.40
     top
    -0.39
    IER
    -0.37
    IERS
    -0.36
     للاسماء
    -0.36
    Predecesor
    -0.35
    top
    -0.35
    RIER
    -0.35
    XmlAccessType
    -0.35
    POSITIVE LOGITS
    Билгалдахарш
    0.91
    ConstraintMaker
    0.76
    IndentedString
    0.73
     isNameExpr
    0.72
    posedge
    0.70
    onAttach
    0.70
    الحياه
    0.69
     uParam
    0.68
    uxxxx
    0.68
    fromnode
    0.68
    Activations Density 1.961%

    No Known Activations