© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 195017
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_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
    -
    0.56
    "
    0.55
    h
    0.54
    u
    0.49
    im
    0.48
    is
    0.48
    ↵
    0.47
    fon
    0.47
    l
    0.47
    casting
    0.47
    POSITIVE LOGITS
     ос
    0.61
     ле
    0.54
     дуже
    0.54
     பாதுகாப்பு
    0.54
     дом
    0.52
     കൃ
    0.51
     Мор
    0.51
     வண்ணப்பூச்சு
    0.50
     Radcliffe
    0.50
     бе
    0.50
    Activations Density 0.000%

    No Known Activations