© 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. 9826
    Prev
    Next
    INDEX
    Explanations

    symbol table

    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
     scholarship
    0.22
     постави
    0.20
     standstill
    0.20
     disorder
    0.20
     再
    0.20
     manifest
    0.20
     muziek
    0.20
    urid
    0.19
     scholar
    0.19
     pathology
    0.19
    POSITIVE LOGITS
    apellido
    0.24
    㭐
    0.22
    ┻
    0.22
    Fifty
    0.21
     Fifty
    0.21
    Emily
    0.21
     ludzi
    0.21
     Новый
    0.21
     نهایت
    0.21
     Shelton
    0.20
    Activations Density 0.000%

    No Known Activations