© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75700
    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_31_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
     किस
    0.40
     कृ
    0.36
    ภู
    0.35
    裾
    0.35
     Elevations
    0.35
    ওনা
    0.34
    커
    0.34
     बद
    0.34
    ębior
    0.34
    釐
    0.34
    POSITIVE LOGITS
     understandably
    0.77
     understandable
    0.71
     rightfully
    0.54
     reação
    0.49
     réaction
    0.47
     rightly
    0.47
     reacción
    0.46
     реак
    0.45
    反应
    0.44
     reaction
    0.44
    Activations Density 0.134%

    No Known Activations