© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6403
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms, especially in the context of biological processes, politics, and food science.

    oai_token-act-pair · gemini-2.0-flash

    additives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     as
    -1.59
     sebagai
    -1.02
     као
    -0.87
     ως
    -0.84
     качестве
    -0.84
     kao
    -0.82
     jako
    -0.80
    作為
    -0.80
     як
    -0.79
     как
    -0.77
    POSITIVE LOGITS
    <bos>
    0.67
     виправивши
    0.66
     kaarangay
    0.62
    évaluateur
    0.60
     متعلقه
    0.59
     beginnetje
    0.57
     Efq
    0.56
     PeEnEo
    0.55
     "'",
    0.50
     NSCoder
    0.49
    Activations Density 9.112%

    No Known Activations