© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207109
    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
    ной
    0.53
    ೕ
    0.52
    願い
    0.52
    ᱮ
    0.52
     decidiu
    0.52
     решил
    0.51
     seductive
    0.50
     squaring
    0.50
    ी
    0.50
     хоче
    0.49
    POSITIVE LOGITS
     I
    0.58
    '/
    0.50
    acan
    0.49
    (
    0.49
    ivät
    0.48
     Mr
    0.48
     (
    0.47
     F
    0.46
     ö
    0.46
     Il
    0.46
    Activations Density 0.000%

    No Known Activations