© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83938
    Prev
    Next
    INDEX
    Explanations

    admitting limitations

    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_23_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
    fieldContext
    0.42
     pericol
    0.40
     LoginComponent
    0.40
     इस्लाम
    0.40
    publique
    0.39
     paralle
    0.39
    껭
    0.38
    ṕ
    0.38
    asciiPanel
    0.38
     तालि
    0.38
    POSITIVE LOGITS
     capabilities
    0.39
     loud
    0.38
     referral
    0.38
    ITT
    0.37
     quick
    0.36
    ILLS
    0.36
     colleagues
    0.36
    CT
    0.36
     duties
    0.36
    眼
    0.36
    Activations Density 0.095%

    No Known Activations