© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9622
    Prev
    Next
    INDEX
    Explanations

    EntityFramework DbContext

    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_13_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
     прибли
    0.31
    वर्षी
    0.29
    ');//
    0.28
    犸
    0.28
    itudini
    0.27
    辮
    0.27
     خصوص
    0.26
     ಅದನ್ನು
    0.26
    akkhand
    0.26
     jornalista
    0.26
    POSITIVE LOGITS
     name
    0.28
     hospital
    0.27
     baan
    0.27
     Rosal
    0.27
    Permission
    0.26
     `
    0.26
     scary
    0.26
     shoe
    0.25
    do
    0.25
     resonance
    0.25
    Activations Density 0.001%

    No Known Activations