© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4899
    Prev
    Next
    INDEX
    Explanations

    words related to some kind of experiment or methodology.

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     was
    -0.94
     previously
    -0.91
     recently
    -0.80
     took
    -0.75
     went
    -0.75
    was
    -0.74
     had
    -0.73
     wasn
    -0.73
     Previously
    -0.73
    Previously
    -0.73
    POSITIVE LOGITS
     preſent
    0.69
    )";
    0.69
    पया
    0.68
     للاسماء
    0.68
    extendable
    0.67
     Theſe
    0.67
     daqui
    0.65
     كومونز
    0.64
     amanhã
    0.62
     auffi
    0.61
    Activations Density 4.450%

    No Known Activations