Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14265
    Prev
    Next
    INDEX
    Explanations

    words related to bodies, computers, and watching things

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Refrain
    -0.51
    ORMAL
    -0.50
     Costello
    -0.50
     preliminar
    -0.50
     Andrade
    -0.49
     preoperative
    -0.49
    chitis
    -0.49
    urez
    -0.49
    cieli
    -0.48
    gående
    -0.48
    POSITIVE LOGITS
     idéia
    0.68
    berdayakan
    0.63
     comigo
    0.63
     linkovi
    0.60
    guém
    0.59
    Datuak
    0.58
     doInBackground
    0.58
    RenderAtEndOf
    0.56
    <bos>
    0.56
    ividual
    0.56
    Activations Density 4.845%

    No Known Activations