© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 36021
    Prev
    Next
    INDEX
    Explanations

    please followed by action

    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
    ↵
    1.45
    </h2>
    0.97
    де
    0.71
    ป
    0.70
     Ekonomi
    0.68
    л
    0.68
    습니다
    0.67
    </h1>
    0.66
    to
    0.65
    the
    0.61
    POSITIVE LOGITS
     of
    0.93
    ore
    0.78
     was
    0.75
     cinq
    0.74
     we
    0.72
     parece
    0.72
     implique
    0.71
     in
    0.70
     femmes
    0.70
     aficionados
    0.69
    Activations Density 0.063%

    No Known Activations