© 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. 129273
    Prev
    Next
    INDEX
    Explanations

    outdoor contexts

    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
    า
    1.43
    ו
    1.20
     дані
    1.03
    ִי
    1.01
     μέρος
    1.00
     данни
    1.00
    arları
    0.99
    ิ
    0.97
    <0xB2>
    0.97
    ৫
    0.97
    POSITIVE LOGITS
     to
    1.41
     at
    1.25
     in
    1.22
    s
    1.12
    他
    1.09
    로
    0.96
     that
    0.95
     as
    0.95
    ku
    0.95
    d
    0.93
    Activations Density 0.001%

    No Known Activations