© 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. 138574
    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
    čiai
    0.41
     textile
    0.37
    playback
    0.36
    籲
    0.36
    %=
    0.35
     Brack
    0.35
    EIS
    0.35
    fts
    0.34
     Brat
    0.34
    ્લે
    0.34
    POSITIVE LOGITS
     понимать
    0.39
     সবুজ
    0.38
     sigma
    0.38
    涜
    0.37
     Preservation
    0.37
    ricted
    0.37
     списке
    0.37
     провод
    0.37
    Repartition
    0.36
     иссле
    0.36
    Activations Density 0.000%

    No Known Activations