© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235799
    Prev
    Next
    INDEX
    Explanations

    expletive shit

    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_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    7
    0.35
     jem
    0.32
     \%$
    0.31
     .-
    0.30
     forme
    0.30
     .'
    0.30
    xty
    0.29
     ವಿಶ
    0.29
     shift
    0.29
     Merchant
    0.29
    POSITIVE LOGITS
    Affect
    0.38
    銥
    0.37
    STRU
    0.34
    σταση
    0.34
     παρα
    0.34
    voud
    0.34
    CAS
    0.32
    affect
    0.32
    ্ু
    0.31
     किरणों
    0.31
    Activations Density 0.000%

    No Known Activations