© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2290
    Prev
    Next
    INDEX
    Explanations

    state management libraries

    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_39_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
     broadcasters
    0.44
    ಾವಣ
    0.42
     individualized
    0.40
     এড়িয়ে
    0.40
    直播
    0.39
    氓
    0.39
    াহিয়ার
    0.39
     independencia
    0.38
    鋃
    0.38
     amortization
    0.37
    POSITIVE LOGITS
    Con
    0.47
    con
    0.45
     Schen
    0.43
    EOL
    0.43
    Bibli
    0.40
     Pyr
    0.39
    Pyr
    0.39
    Und
    0.38
    POSAL
    0.38
     und
    0.38
    Activations Density 0.007%

    No Known Activations