© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136372
    Prev
    Next
    INDEX
    Explanations

    Content Security Policy directives

    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
    。（
    0.57
    يس
    0.54
    Tunnel
    0.49
    ᓄ
    0.47
    ۇل
    0.46
    ヴ
    0.46
     leopard
    0.45
     webcam
    0.45
    تح
    0.44
    誇
    0.44
    POSITIVE LOGITS
    id
    0.67
    it
    0.56
    quiry
    0.55
     Guth
    0.54
    rscheinlich
    0.52
     Galerie
    0.52
     Ons
    0.51
     Type
    0.51
     Hyg
    0.50
    ysta
    0.50
    Activations Density 0.002%

    No Known Activations