© 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. 18033
    Prev
    Next
    INDEX
    Explanations

    hyponatremia

    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
     Marcus
    0.54
     MPG
    0.54
     MG
    0.53
     F
    0.52
     फड
    0.52
     Riemannian
    0.50
     FAO
    0.50
    लिड
    0.50
     FP
    0.49
     planis
    0.49
    POSITIVE LOGITS
    któ
    0.57
    ați
    0.54
    𝕂
    0.54
    ższ
    0.52
    Cristiano
    0.52
     দেশ
    0.50
    䣷
    0.50
    ktan
    0.50
    西哥
    0.48
    apache
    0.48
    Activations Density 0.002%

    No Known Activations