© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11409
    Prev
    Next
    INDEX
    Explanations

    general words that could indicate something about politics, economics, or policies.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Paglinawan
    -0.76
     newBuilder
    -0.73
    DispatchToProps
    -0.72
    ]--;
    -0.71
     transpiration
    -0.69
    مصادر
    -0.69
     tslint
    -0.68
     <<<<<<<<<<<<<<
    -0.65
     oprot
    -0.65
    PropertyChanging
    -0.65
    POSITIVE LOGITS
     Africans
    0.39
    "}>
    0.38
    ________________
    0.38
     bills
    0.38
    ))->
    0.37
    Datuak
    0.37
     Bills
    0.36
     groups
    0.36
     bø
    0.36
    ),),
    0.35
    Activations Density 4.531%

    No Known Activations