© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25261
    Prev
    Next
    INDEX
    Explanations

    goose

    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_10_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
     have
    0.78
     A
    0.72
     JM
    0.71
     were
    0.71
     EXIT
    0.71
     Have
    0.69
     addicted
    0.69
     intravenous
    0.68
     IMF
    0.68
     Tipper
    0.67
    POSITIVE LOGITS
    ش
    0.99
    ك
    0.88
    ع
    0.85
    تي
    0.82
    ق
    0.82
    ض
    0.80
    راتيج
    0.77
    ي
    0.76
    чем
    0.75
    ظ
    0.75
    Activations Density 0.004%

    No Known Activations