© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126183
    Prev
    Next
    INDEX
    Explanations

    might be verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    ه
    0.95
    ก
    0.76
    r
    0.75
    ból
    0.72
    ből
    0.71
    t
    0.64
    ي
    0.61
    ق
    0.61
    y
    0.61
     avrà
    0.60
    POSITIVE LOGITS
    K
    1.00
    在
    0.81
    of
    0.79
    ма
    0.77
    1
    0.73
     في
    0.72
    ‌های
    0.71
    TS
    0.70
     в
    0.70
    ‌ها
    0.68
    Activations Density 0.001%

    No Known Activations