© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208442
    Prev
    Next
    INDEX
    Explanations

    when script is run directly

    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_20_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
    писы
    0.36
     tepat
    0.35
     వ‌
    0.34
    锆
    0.34
     mammoth
    0.33
     berharap
    0.33
    犃
    0.33
    陖
    0.33
    alya
    0.33
     Zer
    0.33
    POSITIVE LOGITS
    ქმედ
    0.35
     dialogo
    0.33
     despert
    0.31
     dialogue
    0.31
    resume
    0.31
    ደር
    0.30
    severity
    0.30
    סטר
    0.30
    Dialogue
    0.30
    ahuasca
    0.29
    Activations Density 0.001%

    No Known Activations