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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1670
    Prev
    Next
    INDEX
    Explanations

    a variety of mostly meaningless tokens unless one looks for co-occurences such as "Profile at"

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    Â
    -0.89
    ”
    -0.77
    </strong>
    -0.73
    ”?
    -0.71
     
    -0.71
    ·
    -0.71
    “
    -0.69
    <em>
    -0.69
    )$
    -0.69
    –
    -0.68
    POSITIVE LOGITS
     avoient
    1.13
     feroit
    1.13
     étoient
    1.08
     auroit
    1.08
     pouvoit
    1.01
     étoit
    0.98
     enfans
    0.93
     élas
    0.84
     démocr
    0.84
     ainfi
    0.79
    Activations Density 1.392%

    No Known Activations