© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18915
    Prev
    Next
    INDEX
    Explanations

    mosquito dunks

    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_15_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
    establishing
    0.48
    ਯ
    0.47
    є
    0.47
    he
    0.47
    im
    0.47
    aki
    0.45
    optimal
    0.45
    ખ
    0.45
    Palm
    0.45
     bahwa
    0.45
    POSITIVE LOGITS
     ಅನೇಕ
    0.55
    städter
    0.55
     الرا
    0.54
     niên
    0.51
     insinu
    0.49
     Ligue
    0.49
    bsch
    0.48
    ടുത്ത
    0.48
     auß
    0.48
    输出
    0.47
    Activations Density 0.000%

    No Known Activations