© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15182
    Prev
    Next
    INDEX
    Explanations

    math formulas and notation

    oai_token-act-pair · gemini-2.0-flash

    \

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    <bos>
    -0.90
    GraphicsUnit
    -0.71
    ThroughAttribute
    -0.54
     Roskov
    -0.51
    passes
    -0.49
    pass
    -0.48
    ̍t
    -0.47
    bootstrapcdn
    -0.47
    Pass
    -0.46
    /******/
    -0.45
    POSITIVE LOGITS
     trier
    0.63
     connexes
    0.59
     PyTuple
    0.59
    ViewImports
    0.58
    datalist
    0.56
     BoxFit
    0.54
    setAdapter
    0.53
    tryck
    0.53
    gucigalpa
    0.52
    ghana
    0.52
    Activations Density 20.672%

    No Known Activations