© 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. 41473
    Prev
    Next
    INDEX
    Explanations

    role in

    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
    1
    0.73
    and
    0.70
    Above
    0.69
    Z
    0.69
    five
    0.67
    ك
    0.67
    O
    0.66
    Canvas
    0.65
    ח
    0.64
    Bey
    0.64
    POSITIVE LOGITS
    šte
    0.75
     is
    0.71
    u
    0.68
     was
    0.66
    亍
    0.66
    습니다
    0.64
    ные
    0.62
    ется
    0.60
     Util
    0.60
    ५
    0.60
    Activations Density 0.033%

    No Known Activations