© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59091
    Prev
    Next
    INDEX
    Explanations

    gasser, casserole, yasser

    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
    在
    1.44
     in
    1.33
    lc
    1.31
    การ
    1.27
    ail
    1.26
    ;
    1.20
    lot
    1.18
     a
    1.16
    larda
    1.16
    lah
    1.16
    POSITIVE LOGITS
    де
    1.20
    يل
    1.20
    тор
    1.16
    تي
    1.13
    ся
    1.11
    ну
    1.09
    েও
    1.09
    ತ್ಯ
    1.08
    ية
    1.05
    ್ದ
    1.05
    Activations Density 0.000%

    No Known Activations