© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200035
    Prev
    Next
    INDEX
    Explanations

    file

    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_50_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
    FO
    0.37
     Angew
    0.37
    бив
    0.36
    赅
    0.36
    inherit
    0.36
    வியல்
    0.35
    FORE
    0.35
     Latest
    0.35
    Introdu
    0.34
    Unified
    0.34
    POSITIVE LOGITS
    as
    0.44
    สต
    0.42
     ด
    0.38
     gost
    0.37
     الد
    0.37
     ದೊ
    0.36
     Sv
    0.35
    enst
    0.35
     contradicting
    0.35
     asap
    0.35
    Activations Density 0.008%

    No Known Activations