© 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. 46688
    Prev
    Next
    INDEX
    Explanations

    et o

    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
    ،
    0.82
    وڈ
    0.74
    »،
    0.66
    و
    0.64
    เรา
    0.64
    ویت
    0.63
    ؛
    0.63
    ur
    0.62
    </b>
    0.62
     solvency
    0.60
    POSITIVE LOGITS
     Siempre
    0.67
     Muchas
    0.64
     Cualquier
    0.62
     Qualquer
    0.61
     Gerade
    0.61
     Sempre
    0.61
     Austausch
    0.60
    nemen
    0.60
    hasOwnProperty
    0.60
     Normalmente
    0.60
    Activations Density 0.003%

    No Known Activations