© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139892
    Prev
    Next
    INDEX
    Explanations

    code definition keyword

    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_12_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
     .)
    0.50
    性と
    0.48
     Graphs
    0.46
     r
    0.44
     ב
    0.44
     Welles
    0.44
     );
    0.44
     누가
    0.44
     ZDF
    0.44
     Deutsche
    0.43
    POSITIVE LOGITS
    sé
    0.57
    \
    0.54
    s
    0.53
    사
    0.52
    -
    0.51
    ans
    0.49
    ktion
    0.49
    plica
    0.48
    par
    0.48
    秇
    0.48
    Activations Density 0.001%

    No Known Activations