© 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. 104281
    Prev
    Next
    INDEX
    Explanations

    falls

    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
     are
    1.82
     can
    1.70
     is
    1.31
    ۔
    1.27
     will
    1.23
    can
    1.22
     would
    1.19
     a
    1.14
     has
    1.14
    ci
    1.14
    POSITIVE LOGITS
    unkt
    1.15
    ل
    1.09
    ER
    0.99
     مختلف
    0.99
    就是要
    0.98
     podendo
    0.98
    henyl
    0.97
     indiquer
    0.95
     besonderen
    0.95
     Begins
    0.94
    Activations Density 0.000%

    No Known Activations