© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78365
    Prev
    Next
    INDEX
    Explanations

    oregano, Kosugi, refugi

    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_0_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
    ل
    1.77
    ك
    1.57
    lara
    1.34
    كره
    1.34
     electrón
    1.31
     banyaknya
    1.30
    كار
    1.30
     diarias
    1.28
    مي
    1.27
    ла
    1.25
    POSITIVE LOGITS
    (
    1.85
    ہ
    1.70
    the
    1.33
    t
    1.11
    y
    1.10
    ach
    1.07
    .
    1.07
     the
    1.05
    il
    1.02
    ()
    1.02
    Activations Density 0.000%

    No Known Activations