© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172007
    Prev
    Next
    INDEX
    Explanations

    file system operations

    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_20_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
     Джор
    0.45
    Rut
    0.44
    φαν
    0.43
    Wol
    0.41
    Goodbye
    0.41
    Enders
    0.41
    鑒
    0.41
     इसने
    0.41
    Ϊ
    0.40
    Fear
    0.40
    POSITIVE LOGITS
     witte
    0.52
     bhai
    0.50
     tais
    0.47
     seront
    0.46
     logical
    0.46
    痢
    0.46
     masing
    0.46
     acl
    0.45
    acock
    0.45
     biru
    0.45
    Activations Density 0.002%

    No Known Activations