© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127448
    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_37_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
    itelja
    0.41
     täht
    0.39
    VIS
    0.38
    മോ
    0.37
     Supporting
    0.37
     Solve
    0.37
     ø
    0.36
     verb
    0.36
     પ્રવેશ
    0.36
     マルチ
    0.36
    POSITIVE LOGITS
    筤
    0.42
     assurances
    0.37
     कृपा
    0.36
    เคล
    0.35
    ឈ្មោះ
    0.35
     watering
    0.34
    ាវ
    0.34
     lakes
    0.34
     lawns
    0.34
    支出
    0.33
    Activations Density 0.000%

    No Known Activations