© 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. 131194
    Prev
    Next
    INDEX
    Explanations

    meth

    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
    antoor
    0.42
     সার
    0.40
    말
    0.40
    诙
    0.39
     こ
    0.39
     प्रमाणपत्र
    0.38
    Civ
    0.38
    こ
    0.37
     Cindy
    0.37
     hunting
    0.37
    POSITIVE LOGITS
    hami
    0.39
    譜
    0.38
    렐
    0.38
    IsNullOrEmpty
    0.37
    痉
    0.37
    achella
    0.37
    otene
    0.36
     Herc
    0.36
     스토리
    0.36
    llen
    0.36
    Activations Density 0.000%

    No Known Activations