© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26698
    Prev
    Next
    INDEX
    Explanations

    limited time offers

    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_10_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
     ćemo
    0.60
     će
    0.59
    YA
    0.57
    のエ
    0.57
    때
    0.57
    ലെ
    0.55
     숫자
    0.55
    n
    0.55
     Time
    0.54
     და
    0.54
    POSITIVE LOGITS
    <0x0D>
    0.55
    utives
    0.49
    </h2>
    0.48
     availed
    0.48
    itories
    0.48
    finement
    0.48
     hastened
    0.48
    வாய
    0.47
    راتيج
    0.47
    paralleled
    0.46
    Activations Density 0.048%

    No Known Activations