© 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. 36118
    Prev
    Next
    INDEX
    Explanations

    kid-friendly

    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
    asını
    0.63
    nya
    0.61
     (
    0.59
    ா
    0.59
    ва
    0.58
    '
    0.58
     are
    0.57
     ও
    0.55
     heredity
    0.55
     afecta
    0.55
    POSITIVE LOGITS
    っ
    0.65
    "。
    0.60
     विज्ञान
    0.59
    ال
    0.59
    بر
    0.59
    الش
    0.57
    ト
    0.57
    غير
    0.56
    الح
    0.56
    Фи
    0.56
    Activations Density 0.001%

    No Known Activations