© 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. 19222
    Prev
    Next
    INDEX
    Explanations

    real-world

    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
    ượu
    0.56
    armée
    0.53
     आतंकवाद
    0.53
    အ
    0.52
    ıç
    0.51
     tomu
    0.50
     economía
    0.50
    izde
    0.50
     Mannschaft
    0.49
    ढ
    0.49
    POSITIVE LOGITS
     effortless
    0.50
     newer
    0.49
    b
    0.47
     stir
    0.46
     incorporate
    0.46
     galvanic
    0.45
    െയി
    0.45
    เช
    0.45
     بونس
    0.44
     простых
    0.44
    Activations Density 0.010%

    No Known Activations