© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20702
    Prev
    Next
    INDEX
    Explanations

    rules and conditions

    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_56_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
    .​​
    0.39
    }.${
    0.38
    谄
    0.38
    `.
    0.37
    跇
    0.37
    澄
    0.34
     】,
    0.33
    .$(
    0.33
    .‏
    0.33
    ய்ட
    0.33
    POSITIVE LOGITS
    
    0.35
    rying
    0.35
    ằ
    0.35
    اریخ
    0.34
     ¿
    0.34
    ($"
    0.33
    ₫
    0.33
    ↵
    0.32
    riet
    0.32
    Trunc
    0.32
    Activations Density 0.814%

    No Known Activations