© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197967
    Prev
    Next
    INDEX
    Explanations

    /

    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
    犾
    0.40
    бере
    0.40
    κτη
    0.40
    கொ
    0.38
    mediate
    0.37
    وفر
    0.37
    oulders
    0.37
    geke
    0.35
     nail
    0.35
    పురం
    0.35
    POSITIVE LOGITS
     Lib
    0.42
    VH
    0.41
     VH
    0.40
     precepts
    0.40
    ާ
    0.39
    RectangleShape
    0.38
    Lib
    0.37
     Personnel
    0.37
     Continuando
    0.36
    ǎ
    0.36
    Activations Density 0.003%

    No Known Activations