© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35802
    Prev
    Next
    INDEX
    Explanations

    foreign greetings and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    t
    0.75
    υ
    0.74
    ç
    0.65
    diphenyl
    0.63
    ل
    0.62
    diamond
    0.61
    dairy
    0.61
    お金
    0.61
    ч
    0.60
    т
    0.59
    POSITIVE LOGITS
    0
    0.86
    ং
    0.64
    entlich
    0.63
    Except
    0.63
    ٠
    0.62
     كانت
    0.61
    ן
    0.61
    తో
    0.60
     что
    0.60
     функ
    0.60
    Activations Density 0.005%

    No Known Activations