© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41460
    Prev
    Next
    INDEX
    Explanations

    WGA

    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_3_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
    ב
    0.78
    ↵
    0.76
    з
    0.66
     gön
    0.64
     CNC
    0.63
     REIT
    0.60
     DBMS
    0.59
     CU
    0.58
     to
    0.57
     TÜ
    0.57
    POSITIVE LOGITS
    c
    0.97
    ной
    0.79
    x
    0.79
    ie
    0.77
    E
    0.75
    S
    0.73
    O
    0.72
    em
    0.70
    ad
    0.69
    baren
    0.69
    Activations Density 0.003%

    No Known Activations