© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13376
    Prev
    Next
    INDEX
    Explanations

    navigate

    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
    িন
    0.71
    (
    0.70
    {
    0.69
    ಾ
    0.66
    ম
    0.63
    डी
    0.61
    া
    0.59
    ौ
    0.57
    ন
    0.56
     år
    0.55
    POSITIVE LOGITS
     conson
    0.65
    し
    0.64
    ள்ளனர்
    0.62
     overcrow
    0.62
    ljivo
    0.62
    comers
    0.61
    ab
    0.60
    cknow
    0.58
     KeyEvent
    0.58
     inconsider
    0.57
    Activations Density 0.028%

    No Known Activations