© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197547
    Prev
    Next
    INDEX
    Explanations

    companion or elder

    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_4_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
    ی
    0.82
    ۔
    0.81
    는
    0.80
    は
    0.79
    ።
    0.77
    ໃນ
    0.73
    И
    0.71
     rebellious
    0.70
    נ
    0.70
    २
    0.69
    POSITIVE LOGITS
    at
    1.00
    as
    0.99
    om
    0.82
    os
    0.75
    ור
    0.74
    ad
    0.73
    us
    0.71
    for
    0.69
    ong
    0.68
    eket
    0.68
    Activations Density 0.000%

    No Known Activations