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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193412
    Prev
    Next
    INDEX
    Explanations

    suffixes denoting state or ability

    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_4_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
    ٢
    1.23
    ﺍ
    0.99
    ،
    0.98
     común
    0.95
    ٣
    0.91
    ේ
    0.89
    ς
    0.89
    ﯼ
    0.89
    想
    0.88
    ली
    0.87
    POSITIVE LOGITS
    im
    1.45
    f
    1.22
    in
    1.11
    a
    1.09
    j
    1.08
    ad
    1.01
    ص
    0.98
    ע
    0.97
    v
    0.96
    ong
    0.95
    Activations Density 0.002%

    No Known Activations