© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 4402
    Prev
    Next
    INDEX
    Explanations

    4/0, 20cm, straightened wire

    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_38_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
     ¼
    0.63
    ¼
    0.57
    ⅜
    0.56
     quarter
    0.54
     pea
    0.43
     peas
    0.42
    厚
    0.42
    pase
    0.41
    圣
    0.41
     ½
    0.40
    POSITIVE LOGITS
     Ali
    0.39
     DuPont
    0.38
     Dand
    0.37
     learning
    0.37
     Lou
    0.37
    ექტ
    0.37
     Jam
    0.36
     Dupree
    0.36
     tro
    0.36
     Tanger
    0.36
    Activations Density 0.041%

    No Known Activations