© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231542
    Prev
    Next
    INDEX
    Explanations

    promoted

    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_6_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
    .
    1.50
    :
    0.95
     at
    0.95
    /
    0.93
    !
    0.92
    ?
    0.92
     the
    0.86
    ல்
    0.85
    et
    0.83
     for
    0.80
    POSITIVE LOGITS
     イベント
    1.13
    trashItem
    1.05
    "];
    1.03
     echoed
    1.01
     ተግባ
    0.97
    vVertex
    0.96
     imasmim
    0.95
     objected
    0.95
     Ал
    0.93
     Современ
    0.93
    Activations Density 0.000%

    No Known Activations