© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145376
    Prev
    Next
    INDEX
    Explanations

    Bavarian and related concepts

    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_0_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
    -
    1.55
    ন
    1.55
    ر
    1.39
    i
    1.38
    на
    1.33
    r
    1.33
    n
    1.29
    р
    1.28
    ン
    1.28
    ن
    1.25
    POSITIVE LOGITS
    ı
    1.30
    他
    1.25
    ↵↵
    1.20
     is
    1.20
    io
    1.16
    的热
    1.16
    的時間
    1.16
    の発
    1.16
    的价格
    1.13
    的多
    1.13
    Activations Density 0.000%

    No Known Activations