© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88647
    Prev
    Next
    INDEX
    Explanations

    hesitation

    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_11_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
    方法は
    0.64
    س
    0.64
    ش
    0.64
    ೃ
    0.64
    h
    0.63
    I
    0.63
    م
    0.61
    OCS
    0.58
    álen
    0.58
    onds
    0.57
    POSITIVE LOGITS
     Clayton
    0.58
    )....
    0.57
     Kavanaugh
    0.57
    )..
    0.56
    )」
    0.55
     ♦
    0.55
    )”
    0.54
     Everett
    0.54
     Hawthorne
    0.54
    ).
    0.53
    Activations Density 0.001%

    No Known Activations