© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143061
    Prev
    Next
    INDEX
    Explanations

    catch

    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_0_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
    و
    1.80
    .
    1.55
     be
    1.52
    มัน
    1.41
    นี้
    1.40
    ມັນ
    1.37
    ה
    1.33
    ↵
    1.30
    นี่
    1.28
    ס
    1.26
    POSITIVE LOGITS
     laterales
    1.05
    த்தான்
    1.01
     Ε
    0.98
     affirms
    0.97
     confesses
    0.93
     and
    0.92
     ({\
    0.91
    LoginID
    0.91
     elég
    0.91
    FieldNumber
    0.91
    Activations Density 0.001%

    No Known Activations