© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9370
    Prev
    Next
    INDEX
    Explanations

    res followed by 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_13_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
    yser
    0.61
    ulit
    0.54
     c
    0.54
    ólito
    0.53
     व्हाइट
    0.52
    讵
    0.52
    ché
    0.52
    hul
    0.51
     Cher
    0.50
    이션
    0.50
    POSITIVE LOGITS
    ﺓ
    0.55
    ্যাব
    0.50
    ファイルを
    0.50
    สต
    0.50
     মানুষদের
    0.49
     velho
    0.49
     fenomeni
    0.49
     anesthesia
    0.48
     punishment
    0.47
     mentality
    0.47
    Activations Density 0.004%

    No Known Activations