© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110704
    Prev
    Next
    INDEX
    Explanations

    forte activity, volonté, participation

    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_2_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
     commencer
    1.15
     on
    1.13
     yapt
    0.99
    л
    0.96
     estern
    0.95
     powied
    0.95
    ের
    0.91
    いろいろ
    0.89
    ूथ
    0.89
     இருக்க
    0.88
    POSITIVE LOGITS
    ب
    1.61
    ла
    1.52
    in
    1.51
    ang
    1.35
    مو
    1.35
    ف
    1.31
    rán
    1.26
    خ
    1.25
    منا
    1.20
    ם
    1.20
    Activations Density 0.001%

    No Known Activations