© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157958
    Prev
    Next
    INDEX
    Explanations

    off-kilter

    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_2_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
    1.45
    ية
    1.38
    -
    1.32
     are
    1.13
     ﺍ
    1.05
    ?’”
    1.02
    ৬
    1.02
    (-
    1.01
    ท
    1.01
    $-$
    1.00
    POSITIVE LOGITS
    ش
    1.31
    ோ
    1.27
    ang
    1.20
    ज
    1.00
     начну
    0.98
    ist
    0.97
    ai
    0.93
    ites
    0.93
    ି
    0.93
    In
    0.93
    Activations Density 0.000%

    No Known Activations