© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123986
    Prev
    Next
    INDEX
    Explanations

    CSS selectors for IDs

    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_37_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
    名为
    0.52
     _
    0.50
     `
    0.49
     chiamato
    0.48
     llamada
    0.46
     ’
    0.46
     '_
    0.46
     chiamata
    0.46
     bernama
    0.46
     washington
    0.46
    POSITIVE LOGITS
    ¿
    0.39
     Serviço
    0.39
    ','')
    0.36
    Ầ
    0.34
    ached
    0.34
    アンド
    0.34
    換
    0.34
     Proper
    0.33
    quirer
    0.33
    USING
    0.33
    Activations Density 0.049%

    No Known Activations