© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207580
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    ♏
    0.59
    ključ
    0.54
     bölümde
    0.53
    hentication
    0.53
    ühren
    0.52
    当初
    0.52
     দেবযানী
    0.52
    gcash
    0.51
     주장
    0.50
    uangan
    0.49
    POSITIVE LOGITS
     z
    0.65
     -
    0.56
     sets
    0.54
    (
    0.50
     gathering
    0.48
     comer
    0.47
    0.47
     ز
    0.46
     fits
    0.46
    _
    0.46
    Activations Density 0.000%

    No Known Activations