© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13901
    Prev
    Next
    INDEX
    Explanations

    colons, numbers, and parenthetical punctuation, often adjacent to capitalized words or symbols related to sources or lists.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ,
    -0.91
     and
    -0.74
    .
    -0.72
    ;
    -0.69
    /
    -0.69
    /');
    -0.65
    :
    -0.63
    ',
    -0.59
    ),
    -0.58
    .
    -0.58
    POSITIVE LOGITS
    Personendaten
    0.73
     Shakspeare
    0.68
     vermelhas
    0.61
     Agamemnon
    0.61
     Coachella
    0.61
     Abonnez
    0.61
     Serap
    0.59
     Armageddon
    0.59
     Sopho
    0.59
     Jop
    0.59
    Activations Density 7.696%

    No Known Activations