© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31659
    Prev
    Next
    INDEX
    Explanations

    say "Ch" 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_50_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
     நெடு
    0.38
     BBB
    0.37
    ബി
    0.36
    榊
    0.36
     Peking
    0.36
     bromine
    0.36
     koperasi
    0.34
     Klin
    0.34
    ᄋ
    0.34
    菩
    0.33
    POSITIVE LOGITS
     CH
    1.01
     Ч
    0.99
    CH
    0.89
     ચ
    0.88
    chi
    0.87
     ਚ
    0.86
     치
    0.84
     chi
    0.84
     Ç
    0.84
     ch
    0.83
    Activations Density 0.026%

    No Known Activations