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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229990
    Prev
    Next
    INDEX
    Explanations

    workhorse

    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_6_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
    ン
    1.17
    n
    1.11
    t
    1.05
    q
    0.97
    น
    0.96
     следу
    0.91
    cription
    0.91
    н
    0.91
    ن
    0.91
    g
    0.88
    POSITIVE LOGITS
    ي
    1.13
    ে
    1.12
    ில்
    1.08
     for
    1.07
    OP
    0.97
    ിക്ക
    0.97
    Ws
    0.97
    OC
    0.96
    RO
    0.96
    AS
    0.94
    Activations Density 0.000%

    No Known Activations