© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142702
    Prev
    Next
    INDEX
    Explanations

    umeentzako txiste

    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_0_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
    י
    1.14
    ي
    1.05
    dan
    0.95
     in
    0.93
    li
    0.90
    يّ
    0.89
    ط
    0.86
    ح
    0.85
    ينا
    0.83
     the
    0.82
    POSITIVE LOGITS
     as
    1.00
     retom
    0.88
    ON
    0.87
    ;
    0.84
    have
    0.81
    ).
    0.80
    amento
    0.80
    IS
    0.78
    IC
    0.75
     recorr
    0.75
    Activations Density 0.000%

    No Known Activations