© 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. 176089
    Prev
    Next
    INDEX
    Explanations

    Ч or Ch sound

    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
     коле
    0.80
     col
    0.62
     кол
    0.61
    col
    0.60
    Col
    0.58
     콜
    0.55
     koll
    0.54
     colloid
    0.54
     colch
    0.54
     coll
    0.53
    POSITIVE LOGITS
     Ch
    0.59
     Ч
    0.55
     Ча
    0.54
     ч
    0.49
     ch
    0.47
    Ch
    0.47
     च
    0.46
    Nach
    0.44
    Ч
    0.44
    epro
    0.44
    Activations Density 0.023%

    No Known Activations