© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85749
    Prev
    Next
    INDEX
    Explanations

    democratizing AI

    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_18_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
     industria
    0.25
    Pharmaceutical
    0.24
     pharmaceutical
    0.23
    \
    0.23
    Chand
    0.23
    Agreement
    0.23
     thai
    0.23
    $
    0.23
     if
    0.23
     AGM
    0.23
    POSITIVE LOGITS
     Sobre
    0.22
    သုံး
    0.22
     Perkenalkan
    0.22
     Réponses
    0.21
    proguard
    0.21
     Př
    0.21
    zoom
    0.20
    轉換
    0.20
    oč
    0.20
     Actualmente
    0.20
    Activations Density 0.003%

    No Known Activations