© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177639
    Prev
    Next
    INDEX
    Explanations

    start and progress

    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_29_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
    boxyl
    0.41
     respective
    0.40
    vents
    0.40
    بوب
    0.38
    ')+
    0.37
    슝
    0.37
    条例
    0.37
    odat
    0.37
     분명
    0.36
     androgen
    0.36
    POSITIVE LOGITS
    岘
    0.41
    團隊
    0.38
     délai
    0.38
    踴
    0.37
     wali
    0.37
     الحد
    0.37
     മേഖല
    0.37
    龐
    0.36
     rem
    0.36
     разделе
    0.36
    Activations Density 0.005%

    No Known Activations