© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31101
    Prev
    Next
    INDEX
    Explanations

    code imports and structure

    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_31_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
     diciendo
    0.17
    ска
    0.16
    ὥ
    0.16
    ிகளின்
    0.16
     ভাষায়
    0.15
     mostrando
    0.15
    धिक
    0.15
    ICK
    0.15
    shtml
    0.15
    ():
    0.15
    POSITIVE LOGITS
    లంగా
    0.19
     rendu
    0.18
    este
    0.18
     Freed
    0.17
     школова
    0.17
     قیمت
    0.17
     undergraduate
    0.17
     Underlying
    0.17
     avoidance
    0.17
     Trois
    0.17
    Activations Density 0.002%

    No Known Activations