© 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. 86285
    Prev
    Next
    INDEX
    Explanations

    state laws and authority

    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
    다
    0.73
    of
    0.72
     बड़ी
    0.67
    Л
    0.67
    ка
    0.66
    out
    0.62
    ו
    0.60
    ДУ
    0.58
     बड़ी
    0.57
    и
    0.57
    POSITIVE LOGITS
    -
    1.03
    stion
    0.86
    st
    0.77
    </h3>
    0.73
    ')}
    0.71
    c
    0.71
    রি
    0.71
    stock
    0.68
    terrorism
    0.66
    bellum
    0.64
    Activations Density 0.001%

    No Known Activations