© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63279
    Prev
    Next
    INDEX
    Explanations

    dead

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Quir
    0.42
    ベー
    0.39
    བྱ
    0.38
    णि
    0.38
    金
    0.37
     শাহ
    0.37
     Fee
    0.36
     Cri
    0.36
    Nit
    0.36
     Shah
    0.36
    POSITIVE LOGITS
     dead
    1.29
     Dead
    1.16
    dead
    1.15
    Dead
    1.12
     DEAD
    1.05
    DEAD
    0.95
     डेड
    0.77
    死
    0.75
     मृत
    0.74
     deadlock
    0.71
    Activations Density 0.001%

    No Known Activations