© 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. 13450
    Prev
    Next
    INDEX
    Explanations

    parts of legal documents like citations, references, and section headings

    oai_token-act-pair · gemini-2.0-flash

    research excerpts

    np_max-act-logits · 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
     myſelf
    -0.84
     Efq
    -0.79
     itſelf
    -0.73
     ―――――
    -0.69
     endregion
    -0.69
     leaſt
    -0.69
     purpoſe
    -0.68
     houſe
    -0.68
     raiſ
    -0.68
     Theſe
    -0.68
    POSITIVE LOGITS
     Pre
    0.52
     Man
    0.50
     tillgäng
    0.50
     More
    0.49
     Car
    0.49
     Pat
    0.48
     kvä
    0.47
     Multi
    0.47
     To
    0.46
     Last
    0.46
    Activations Density 15.050%

    No Known Activations