© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235035
    Prev
    Next
    INDEX
    Explanations

    rate

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    蒼
    0.39
    ."'
    0.36
     oscillators
    0.35
    キャン
    0.35
    ';",
    0.35
     بينا
    0.35
     ちゃ
    0.34
     ট্যাঙ্ক
    0.34
    興味
    0.34
    selfobj
    0.34
    POSITIVE LOGITS
     rates
    0.73
     Rates
    0.70
     rate
    0.68
    Rate
    0.68
     Rate
    0.67
    rate
    0.64
    rates
    0.63
    Rates
    0.62
     RATE
    0.61
    率
    0.60
    Activations Density 0.000%

    No Known Activations