© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137270
    Prev
    Next
    INDEX
    Explanations

    `__init__.py`

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    REFERENCE
    0.38
    cdf
    0.38
    RequestHandler
    0.36
    idum
    0.35
    METHOD
    0.34
     ";"
    0.34
    Person
    0.34
     l
    0.33
     METHOD
    0.33
    ஆ
    0.33
    POSITIVE LOGITS
     Pap
    0.48
    撒
    0.41
    Pap
    0.41
    pap
    0.40
     presentations
    0.39
     pap
    0.39
     Cir
    0.39
    imonials
    0.39
    目の
    0.38
     prevailed
    0.38
    Activations Density 0.000%

    No Known Activations