© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227071
    Prev
    Next
    INDEX
    Explanations

    purchased with or items

    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_6_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
    icks
    0.89
    ill
    0.88
    :
    0.87
     tecnológicos
    0.84
     посвящён
    0.80
     बढ़ते
    0.79
     direção
    0.77
     мужчина
    0.76
     fécond
    0.75
    (
    0.73
    POSITIVE LOGITS
    ن
    1.48
    ри
    1.37
    م
    1.35
    ン
    1.26
    ד
    1.20
    ט
    1.19
    س
    1.18
    า
    1.17
    ма
    1.11
    لا
    1.09
    Activations Density 0.001%

    No Known Activations