© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7811
    Prev
    Next
    INDEX
    Explanations

    label for

    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_40_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
    入
    0.36
    තාව
    0.35
    Calc
    0.35
     ダブル
    0.35
    🍗
    0.35
     آسی
    0.34
    炙
    0.34
     khỏe
    0.33
    钙
    0.33
     computable
    0.32
    POSITIVE LOGITS
     ਇਕ
    0.35
    Blending
    0.35
     kid
    0.34
     لان
    0.33
    ufu
    0.33
     Fuk
    0.33
     writes
    0.33
    uste
    0.33
     trucks
    0.33
    exus
    0.33
    Activations Density 0.007%

    No Known Activations