© 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. 207321
    Prev
    Next
    INDEX
    Explanations

    linked list 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
    ueux
    0.43
     tortue
    0.43
    ್ಧ
    0.42
     tùy
    0.42
    ﷻ
    0.40
    clearfix
    0.40
    Aile
    0.40
    いたします
    0.39
    {&
    0.39
    റായി
    0.38
    POSITIVE LOGITS
     Gh
    0.47
     Primary
    0.43
     partis
    0.42
     Г
    0.42
     Generators
    0.42
     carbons
    0.42
    GH
    0.42
     Grain
    0.42
     sosten
    0.41
     Utils
    0.41
    Activations Density 0.001%

    No Known Activations