© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257647
    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_22_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
     dedicating
    0.44
    ადი
    0.43
    estructive
    0.43
     DOI
    0.42
     sacrificing
    0.41
    麃
    0.40
     destin
    0.40
    น
    0.40
    Í
    0.40
     Attendance
    0.40
    POSITIVE LOGITS
    arının
    0.48
    غو
    0.46
     cubrir
    0.43
     dependents
    0.43
     дели
    0.43
    zed
    0.42
    ズ
    0.42
    g
    0.42
    qua
    0.40
     drugih
    0.39
    Activations Density 0.000%

    No Known Activations