© 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. 177633
    Prev
    Next
    INDEX
    Explanations

    section or list delimiter

    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
     Labor
    0.40
    {.
    0.38
     Italy
    0.37
     Justice
    0.36
     Smith
    0.36
     St
    0.36
     Roger
    0.35
     Content
    0.34
     Ad
    0.34
     Ruh
    0.34
    POSITIVE LOGITS
    қи
    0.40
    henol
    0.40
    äv
    0.39
    SpecID
    0.37
     spéc
    0.36
    ┎
    0.36
    ণ্ঠে
    0.36
    ankle
    0.36
    降低
    0.36
    вард
    0.36
    Activations Density 0.045%

    No Known Activations