© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88221
    Prev
    Next
    INDEX
    Explanations

    happy dog wagged

    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
    s
    0.91
    ی
    0.87
    на
    0.83
    ก
    0.83
    다
    0.73
     in
    0.72
    au
    0.70
    at
    0.70
    기
    0.69
    ai
    0.67
    POSITIVE LOGITS
     cataly
    0.69
    '
    0.66
    renner
    0.61
     деву
    0.60
    rául
    0.60
     комплект
    0.59
    länder
    0.59
     प्रकरण
    0.57
    muz
    0.56
    يارات
    0.56
    Activations Density 0.010%

    No Known Activations