© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149232
    Prev
    Next
    INDEX
    Explanations

    dependencies in Cargo.toml

    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_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
    for
    0.47
    if
    0.45
    are
    0.39
    誇
    0.38
    í
    0.38
    来到
    0.38
     राज्यात
    0.38
    ì
    0.38
    still
    0.37
    glia
    0.37
    POSITIVE LOGITS
     procesos
    0.44
     bajas
    0.43
     futbol
    0.41
     ваго
    0.40
     historischen
    0.40
     koop
    0.40
     hydrol
    0.39
     démarrage
    0.39
     baja
    0.39
     reales
    0.39
    Activations Density 0.000%

    No Known Activations