© 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
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 153911
    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_23_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
    РИ
    0.42
    ছেন
    0.42
    ESSIONS
    0.41
    snackbar
    0.41
    핌
    0.41
    SETTINGS
    0.40
     ഏറെ
    0.40
    婉
    0.39
    설
    0.38
     exaggeration
    0.38
    POSITIVE LOGITS
    bes
    0.44
    oman
    0.42
    etan
    0.41
     невозможно
    0.41
    unker
    0.40
    azi
    0.40
    anish
    0.40
    ayı
    0.39
     கரிம
    0.39
    atan
    0.39
    Activations Density 0.000%

    No Known Activations