© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110767
    Prev
    Next
    INDEX
    Explanations

    multi-language word fragments

    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_2_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
     at
    0.54
    E
    0.54
    P
    0.48
    K
    0.48
     of
    0.47
    L
    0.47
    Apa
    0.46
    Foot
    0.46
    i
    0.45
    ۹
    0.45
    POSITIVE LOGITS
    ли
    0.79
    ט
    0.77
    س
    0.72
    с
    0.66
    تر
    0.64
    ל
    0.63
    ला
    0.63
    ف
    0.61
    ب
    0.61
    ن
    0.61
    Activations Density 0.000%

    No Known Activations