© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202493
    Prev
    Next
    INDEX
    Explanations

    patch commands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Lycodon
    0.45
    南海
    0.45
    徎
    0.42
    Brend
    0.41
    的方向
    0.40
     informally
    0.39
    োধনী
    0.39
     வள்ளி
    0.39
    曱
    0.39
     Leinster
    0.38
    POSITIVE LOGITS
    set
    0.42
    export
    0.41
     सेट
    0.41
    CTX
    0.40
     surgi
    0.39
    sets
    0.39
     Sets
    0.39
    设置为
    0.39
    เสียหาย
    0.38
    statement
    0.38
    Activations Density 0.001%

    No Known Activations