© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 164962
    Prev
    Next
    INDEX
    Explanations

    Kishida and Marco Materazzi/Jr

    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_13_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
    session
    0.51
    unused
    0.49
    dismiss
    0.48
     इसलिए
    0.46
    isements
    0.45
     पसंद
    0.45
    bags
    0.45
    ﷺ
    0.45
    repe
    0.45
    ಎಸ್
    0.44
    POSITIVE LOGITS
    Fantasy
    0.61
     valet
    0.54
     cannabin
    0.51
    Point
    0.51
     breach
    0.51
     lifeline
    0.50
     triathlon
    0.50
     candlestick
    0.50
    Camb
    0.50
     renderEncoder
    0.50
    Activations Density 0.000%

    No Known Activations