© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1304
    Prev
    Next
    INDEX
    Explanations

    right to

    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_40_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
    createStatement
    0.41
    ӱ
    0.37
     _)
    0.36
     पुरे
    0.35
    ையில்
    0.34
    |");
    0.34
    ुणा
    0.34
    midnight
    0.34
    :)
    0.34
    涞
    0.34
    POSITIVE LOGITS
     right
    2.06
     diritto
    1.78
     право
    1.77
    Right
    1.75
     direito
    1.74
     حق
    1.73
    right
    1.71
     Right
    1.70
     droit
    1.70
     derecho
    1.68
    Activations Density 0.092%

    No Known Activations