© 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. 158351
    Prev
    Next
    INDEX
    Explanations

    arabic and foreign punctuation

    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
    ка
    1.02
    ك
    0.96
    на
    0.93
    д
    0.92
    ب
    0.91
    ש
    0.85
    و
    0.82
    ா
    0.79
    ה
    0.79
    ст
    0.79
    POSITIVE LOGITS
    n
    0.82
    ።
    0.69
    ۔
    0.68
     j
    0.66
    。
    0.66
     s
    0.64
     h
    0.64
     t
    0.64
     in
    0.64
     l
    0.64
    Activations Density 0.000%

    No Known Activations