© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134802
    Prev
    Next
    INDEX
    Explanations

    treated like

    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_6_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
    ה
    1.05
    1.00
     administración
    0.96
     implemented
    0.93
     divul
    0.91
     authorizations
    0.91
     an
    0.90
    ા
    0.89
    ли
    0.88
     distill
    0.87
    POSITIVE LOGITS
    ners
    0.96
    GaAs
    0.95
     Pairs
    0.93
    -【
    0.93
    inence
    0.91
    WK
    0.91
    Ⅵ
    0.91
    annya
    0.91
    
    0.89
    Wu
    0.89
    Activations Density 0.000%

    No Known Activations