© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9897
    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_13_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
     הס
    0.63
     fout
    0.52
     rebels
    0.50
    侓
    0.49
     ק
    0.49
     باشد
    0.48
     kuma
    0.48
     $)$
    0.48
     الاجتماعية
    0.48
     jossa
    0.48
    POSITIVE LOGITS
    е
    0.52
     EDWARD
    0.52
    ,&
    0.52
    тельством
    0.49
    getTarget
    0.49
    ﻐ
    0.48
    רה
    0.47
     immobile
    0.47
    9
    0.47
    擘
    0.47
    Activations Density 0.000%

    No Known Activations