© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36634
    Prev
    Next
    INDEX
    Explanations

    Object, Item, ID, Value, color, app

    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_11_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
    o
    0.75
    al
    0.75
     is
    0.70
    ться
    0.68
    ul
    0.67
     о
    0.66
     ૩
    0.64
     и
    0.63
    ারী
    0.63
     were
    0.62
    POSITIVE LOGITS
    하다
    0.68
    ）
    0.63
    кать
    0.61
    性
    0.60
    ل
    0.60
    OT
    0.59
    B
    0.59
    Car
    0.58
    Tracks
    0.57
    A
    0.57
    Activations Density 0.019%

    No Known Activations