© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46015
    Prev
    Next
    INDEX
    Explanations

    sphere and occasional hiking

    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_13_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
     Eint
    0.52
    čiti
    0.52
     t
    0.47
    idos
    0.47
     Glückwunsch
    0.46
    BI
    0.46
    лі
    0.45
    Leod
    0.44
    я
    0.44
    ettes
    0.43
    POSITIVE LOGITS
    וריה
    0.50
     دن
    0.50
     якая
    0.47
    ጀም
    0.45
    ൬
    0.45
    مو
    0.44
    輙
    0.44
    рын
    0.43
    تد
    0.43
     ज्यामुळे
    0.42
    Activations Density 0.000%

    No Known Activations