© 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. 38869
    Prev
    Next
    INDEX
    Explanations

    names like Donald, Tim, Percival

    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
     in
    0.87
    ن
    0.77
    ش
    0.70
    art
    0.70
     في
    0.66
    What
    0.66
    在
    0.66
    It
    0.66
    ag
    0.66
    ig
    0.65
    POSITIVE LOGITS
    ı
    1.05
    ী
    0.81
    า
    0.80
    ルの
    0.78
    ९
    0.76
    ८
    0.73
    複数の
    0.72
    ת
    0.71
    ために
    0.70
    ді
    0.68
    Activations Density 0.001%

    No Known Activations