© 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. 18998
    Prev
    Next
    INDEX
    Explanations

    defining

    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
    ulls
    0.46
    ushu
    0.44
    ln
    0.43
    asty
    0.43
    musik
    0.43
    0
    0.43
    awa
    0.42
    2
    0.42
    new
    0.42
    li
    0.42
    POSITIVE LOGITS
    设有
    0.46
     билет
    0.44
     preoc
    0.44
     δο
    0.43
     DQN
    0.42
     الص
    0.42
     εύ
    0.42
    xRt
    0.42
     предусматри
    0.42
     perceptible
    0.41
    Activations Density 0.002%

    No Known Activations