© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177688
    Prev
    Next
    INDEX
    Explanations

    express require

    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_24_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
     Sandy
    0.38
     шли
    0.35
    稻
    0.35
     ([[
    0.35
     calibrate
    0.34
    </
    0.33
     Heav
    0.33
     Experiments
    0.33
    🏻
    0.32
     experiments
    0.32
    POSITIVE LOGITS
     ২০১
    0.46
     hoved
    0.45
     communément
    0.43
     dansk
    0.43
     الأز
    0.42
    ানুভূতি
    0.41
    badan
    0.41
     vü
    0.41
    valued
    0.41
    čné
    0.41
    Activations Density 0.000%

    No Known Activations