© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261387
    Prev
    Next
    INDEX
    Explanations

    motorcycle

    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_5_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
    ла
    1.65
    in
    1.45
    ಮ
    1.19
    𝗖
    1.17
    𝗮
    1.16
    inę
    1.13
    ວ
    1.13
    as
    1.11
    ना
    1.11
    𝗻
    1.08
    POSITIVE LOGITS
    t
    1.46
    í
    1.12
     with
    1.05
    ä
    1.03
    一
    1.03
     on
    0.97
    لي
    0.93
    z
    0.89
    é
    0.83
     or
    0.79
    Activations Density 0.000%

    No Known Activations