© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44780
    Prev
    Next
    INDEX
    Explanations

    big data processing complexity

    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_3_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
    ße
    0.68
    '
    0.67
     různých
    0.59
    }")
    0.58
     těchto
    0.58
     Абра
    0.56
     první
    0.54
     Engaging
    0.54
    ്
    0.54
    ки
    0.54
    POSITIVE LOGITS
    EL
    0.85
    IN
    0.82
    AL
    0.82
    ER
    0.79
    ED
    0.79
    OD
    0.77
    ON
    0.76
    AR
    0.74
    AT
    0.73
    ेड
    0.72
    Activations Density 0.006%

    No Known Activations