© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115238
    Prev
    Next
    INDEX
    Explanations

    code and punctuation delimiters

    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_27_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
     timescales
    0.34
     Their
    0.34
     Documentary
    0.34
     Modern
    0.33
     cosine
    0.33
    ubercul
    0.33
     Duration
    0.32
    )$$
    0.32
     macOS
    0.32
     Reduced
    0.32
    POSITIVE LOGITS
     পাবার
    0.38
    Lista
    0.36
    INGS
    0.35
     সাজেশন
    0.35
    keszt
    0.34
    AppName
    0.34
    ilung
    0.34
     sukham
    0.33
    Carrito
    0.33
    ٻ
    0.33
    Activations Density 0.000%

    No Known Activations