© 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. 46792
    Prev
    Next
    INDEX
    Explanations

    rise and shine

    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
    ia
    0.86
    ing
    0.85
    า
    0.75
    é
    0.70
    ov
    0.70
    lijke
    0.68
    ta
    0.66
    ணும்
    0.66
    ang
    0.65
    ohex
    0.64
    POSITIVE LOGITS
    ص
    0.92
    д
    0.88
    د
    0.86
    ب
    0.84
    ه
    0.81
    ي
    0.79
    두
    0.78
    هم
    0.76
    י
    0.75
    أ
    0.73
    Activations Density 0.001%

    No Known Activations