© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 375
    Prev
    Next
    INDEX
    Explanations

    `[` followed by `tok`, `derive`, or `cfg`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     results
    0.41
    ოდა
    0.38
     introductions
    0.38
     Password
    0.37
     Pino
    0.37
     Bal
    0.36
     namespace
    0.36
     *>
    0.36
    拄
    0.36
     प्राइस
    0.35
    POSITIVE LOGITS
    tok
    0.43
    avis
    0.43
    BITS
    0.41
    crate
    0.39
    cfg
    0.39
    Tok
    0.38
    crates
    0.37
     tok
    0.36
    раст
    0.36
    рованное
    0.36
    Activations Density 0.001%

    No Known Activations