© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169138
    Prev
    Next
    INDEX
    Explanations

    matching

    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_56_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
     세
    1.93
    세
    1.81
     thế
    1.46
    セ
    1.22
    세를
    1.21
     Thế
    1.19
     Се
    1.13
     セ
    1.13
    世
    1.12
    เซ
    1.06
    POSITIVE LOGITS
    ূট
    0.37
    ût
    0.37
     clôt
    0.36
    ర్చి
    0.36
    äng
    0.36
    ented
    0.35
    ąc
    0.35
    tras
    0.35
    Corresponding
    0.35
    iler
    0.34
    Activations Density 0.001%

    No Known Activations