© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167777
    Prev
    Next
    INDEX
    Explanations

    attention seeking

    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_31_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
     mortg
    0.29
     ([
    0.29
     misunder
    0.29
    nesses
    0.28
    ஷன்
    0.28
     (
    0.28
    itability
    0.28
     properties
    0.27
     purses
    0.27
    ([
    0.27
    POSITIVE LOGITS
    百家乐
    0.33
     उल्लेखनीय
    0.33
     Nbd
    0.32
     essi
    0.32
    Tuy
    0.32
     evitare
    0.32
    अभिने
    0.32
     suffisante
    0.31
     sobrevivir
    0.31
     éviter
    0.31
    Activations Density 0.004%

    No Known Activations