© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129487
    Prev
    Next
    INDEX
    Explanations

    shown examples

    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_1_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
    t
    1.57
    ية
    1.19
    a
    1.05
    ון
    1.02
    p
    1.02
     You
    0.96
     on
    0.96
    ა
    0.95
     up
    0.95
    to
    0.95
    POSITIVE LOGITS
     نیز
    0.94
     pièces
    0.91
    nées
    0.89
     broadcasters
    0.89
     decât
    0.89
     eigenfunctions
    0.87
    acies
    0.86
     généralement
    0.86
     ника
    0.86
     voila
    0.86
    Activations Density 0.001%

    No Known Activations