© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209770
    Prev
    Next
    INDEX
    Explanations

    word parts

    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_5_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
    am
    0.39
    3
    0.37
    alten
    0.36
    ib
    0.35
     σε
    0.35
    h
    0.35
    al
    0.32
    iin
    0.32
     vilket
    0.32
     ની
    0.31
    POSITIVE LOGITS
     It
    0.58
     to
    0.57
    ک
    0.56
    л
    0.52
    上
    0.50
    یس
    0.47
     it
    0.47
     at
    0.45
    ü
    0.43
    á
    0.43
    Activations Density 0.000%

    No Known Activations