© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140083
    Prev
    Next
    INDEX
    Explanations

    chance of rain or snow

    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_12_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
    тов
    0.34
    ologiques
    0.34
     Λ
    0.33
     Ε
    0.32
    reciation
    0.32
    ros
    0.32
     Бі
    0.31
     सेल्सियस
    0.30
     মুঠ
    0.30
    tai
    0.30
    POSITIVE LOGITS
    ا
    0.47
    到
    0.36
    如果
    0.35
    eniz
    0.35
    았다
    0.35
    ل
    0.34
    如果你
    0.34
     haunted
    0.34
    ແມ
    0.34
    要
    0.34
    Activations Density 0.003%

    No Known Activations