© 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. 84674
    Prev
    Next
    INDEX
    Explanations

    particle number, size, and behavior

    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
    ו
    1.93
    在
    1.53
    im
    1.45
    gewicht
    1.39
    u
    1.36
    в
    1.34
    ও
    1.34
    و
    1.32
    ин
    1.27
    𝐧
    1.26
    POSITIVE LOGITS
     on
    2.19
     is
    2.09
     at
    1.88
    した
    1.54
     or
    1.51
     to
    1.47
    னர்
    1.46
    1
    1.41
    おり
    1.38
    ều
    1.34
    Activations Density 0.002%

    No Known Activations