© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213433
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    การ
    1.47
    -
    1.44
    ।
    1.35
    ,
    1.34
    ;
    1.30
     یا
    1.20
     reorganization
    1.16
    1.12
    /
    1.12
     artisanal
    1.11
    POSITIVE LOGITS
    in
    1.61
    as
    1.34
    يل
    1.27
    يم
    1.16
    ar
    1.15
    u
    1.14
    on
    1.09
    pl
    1.02
    렇게
    1.02
    مس
    1.02
    Activations Density 0.000%

    No Known Activations