© 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. 171033
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     ২
    0.43
     VII
    0.36
    ǒ
    0.36
     two
    0.35
     surg
    0.35
     six
    0.35
     three
    0.35
     Foreman
    0.34
    aliya
    0.33
     gap
    0.33
    POSITIVE LOGITS
     hundred
    1.32
    Hundred
    1.15
     Hundred
    1.14
    teen
    1.05
    百
    1.02
    десят
    1.01
    hundred
    0.99
    деся
    0.97
     puluh
    0.96
    ty
    0.93
    Activations Density 0.000%

    No Known Activations