© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203833
    Prev
    Next
    INDEX
    Explanations

    currency symbols

    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_56_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
    US
    0.51
     cents
    0.46
    Up
    0.46
    up
    0.46
     dollars
    0.45
    𝗨
    0.45
    Twenty
    0.44
    Thirty
    0.43
    dollar
    0.43
     US
    0.42
    POSITIVE LOGITS
     Предпо
    0.39
     var
    0.35
    ď
    0.35
    分からない
    0.34
    력이
    0.34
     مثبت
    0.34
     éstas
    0.34
     hombres
    0.33
    اقة
    0.33
     সেগুলি
    0.33
    Activations Density 0.000%

    No Known Activations