© 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. 38292
    Prev
    Next
    INDEX
    Explanations

    manager, management

    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
    4
    0.74
    است
    0.67
    mari
    0.67
    入力
    0.66
    াল্ড
    0.66
     право
    0.64
    margin
    0.64
    mocha
    0.63
    1
    0.63
     presentes
    0.63
    POSITIVE LOGITS
    ↵
    0.79
    го
    0.73
    은
    0.69
    리
    0.66
    नंतर
    0.65
    ล
    0.65
     '
    0.62
    ก็
    0.61
    ן
    0.60
    กับการ
    0.59
    Activations Density 0.002%

    No Known Activations