© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126193
    Prev
    Next
    INDEX
    Explanations

    programming code structure

    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_37_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
     bụng
    0.42
    胳
    0.37
     미술
    0.36
     mathemat
    0.35
     Crunch
    0.35
     सॉ
    0.35
    БО
    0.35
     Bollinger
    0.35
     반
    0.35
     Minutes
    0.35
    POSITIVE LOGITS
    kin
    0.39
    yler
    0.38
    workers
    0.36
    genstein
    0.36
    Flame
    0.36
    Mutable
    0.35
     grounded
    0.35
    pw
    0.35
     হয়েছিলেন
    0.35
    list
    0.35
    Activations Density 0.001%

    No Known Activations