© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161429
    Prev
    Next
    INDEX
    Explanations

    get quote or estimate

    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_31_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
     Ayurved
    0.37
    វេល
    0.36
     chromatographic
    0.35
     chromatography
    0.35
    pgamma
    0.35
     Managed
    0.34
     يتيمه
    0.34
    ពេ
    0.33
     Paid
    0.33
    鬻
    0.32
    POSITIVE LOGITS
    Quotes
    0.57
     quotes
    0.55
     Quotes
    0.52
    quotes
    0.51
     quote
    0.49
     quoting
    0.49
     quotations
    0.46
     estimation
    0.45
     estimating
    0.45
    Quote
    0.45
    Activations Density 0.002%

    No Known Activations