© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1207
    Prev
    Next
    INDEX
    Explanations

    references to groups of people, especially students, researchers, advertisers, engineers, or governments

    oai_token-act-pair · gemini-2.0-flash

    people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    httphttps
    -0.97
    rungsseite
    -0.91
    Hochspringen
    -0.79
     defStyle
    -0.78
    帖最后由
    -0.76
    IsMutable
    -0.76
    RectangleBorder
    -0.73
     Efq
    -0.71
    endphp
    -0.71
    PMailer
    -0.70
    POSITIVE LOGITS
     are
    0.91
     were
    0.87
     have
    0.79
     themselves
    0.77
     aren
    0.64
     don
    0.62
     seem
    0.58
     who
    0.58
     need
    0.57
     deserve
    0.54
    Activations Density 1.472%

    No Known Activations