© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193323
    Prev
    Next
    INDEX
    Explanations

    mathematics and related concepts

    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_9_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
     инструк
    0.50
    HDMI
    0.50
    Defer
    0.48
    🏄
    0.48
    후
    0.46
     Octopus
    0.46
     идти
    0.45
     частини
    0.45
     Upgrade
    0.45
    у
    0.44
    POSITIVE LOGITS
     chemist
    0.53
     pola
    0.50
    iee
    0.49
     soil
    0.47
     carboxyl
    0.46
    irr
    0.46
     comunità
    0.46
    om
    0.46
     unreal
    0.46
     carbohydrates
    0.46
    Activations Density 0.000%

    No Known Activations