© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33562
    Prev
    Next
    INDEX
    Explanations

    likely saying / right to

    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_3_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
     площа
    0.57
     destinat
    0.56
     جانب
    0.56
     ñ
    0.55
     შორის
    0.55
    㐰
    0.54
     gaussian
    0.53
     αρχ
    0.53
     randomize
    0.53
     άλ
    0.52
    POSITIVE LOGITS
    is
    0.87
    n
    0.79
    -
    0.71
    o
    0.69
    y
    0.69
    ли
    0.69
    시
    0.68
    e
    0.68
    z
    0.67
    Part
    0.66
    Activations Density 0.103%

    No Known Activations