© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214621
    Prev
    Next
    INDEX
    Explanations

    WT, BWT, DWT, ttw

    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_5_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
    ן
    1.27
    ς
    1.05
    ों
    1.02
    ное
    1.02
    ی
    1.02
    ы
    1.00
    नंतर
    0.99
     площад
    0.95
    aciones
    0.95
     creatividad
    0.95
    POSITIVE LOGITS
    S
    2.05
    L
    1.81
    B
    1.78
    W
    1.78
    Y
    1.73
    K
    1.68
    T
    1.64
    M
    1.61
    D
    1.59
    H
    1.59
    Activations Density 0.001%

    No Known Activations