© 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. 12633
    Prev
    Next
    INDEX
    Explanations

    code and script-like syntax, including commands, file paths, and version numbers.

    oai_token-act-pair · gemini-2.0-flash

    Code/Mathematics

    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
    々
    -0.66
    ppelin
    -0.52
    YY
    -0.50
     cc
    -0.49
    GG
    -0.49
    ఔ
    -0.49
    észetes
    -0.48
     CC
    -0.48
     Италијани
    -0.48
    yy
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.86
    ArgsConstructor
    0.70
    __*/
    0.65
    +#+#
    0.63
    GenerationType
    0.60
    complexContent
    0.58
    NgModule
    0.57
     JSONException
    0.56
    StoreMessageInfo
    0.54
     ujednoznacz
    0.54
    Activations Density 32.030%

    No Known Activations