© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83463
    Prev
    Next
    INDEX
    Explanations

    By [method/time/entity]

    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_0_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
     of
    2.06
    of
    1.79
    ,
    1.42
     (
    1.34
    ของ
    1.32
    ни
    1.30
     and
    1.27
    ing
    1.24
     що
    1.20
    i
    1.17
    POSITIVE LOGITS
    ن
    1.75
    কে
    1.68
    ية
    1.56
     to
    1.55
    ל
    1.54
    ের
    1.44
    ד
    1.39
    ন
    1.34
    لای
    1.30
    িন
    1.28
    Activations Density 0.001%

    No Known Activations