© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24080
    Prev
    Next
    INDEX
    Explanations

    say "c" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    切
    0.54
     切
    0.51
    cuts
    0.50
    cutting
    0.50
     Cutting
    0.50
     cutting
    0.50
     cuts
    0.48
     Cuts
    0.47
     cuttings
    0.46
    Cutting
    0.44
    POSITIVE LOGITS
    C
    1.28
    カ
    1.16
     ка
    1.10
     কা
    0.98
     ค
    0.97
     C
    0.97
     क
    0.91
     カ
    0.88
    のカ
    0.87
     ک
    0.82
    Activations Density 0.038%

    No Known Activations