© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36298
    Prev
    Next
    INDEX
    Explanations

    general overview, timelines, macro

    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_31_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
    Temporary
    0.44
    )}}{
    0.38
    szyst
    0.38
    temporary
    0.37
    selfish
    0.36
     अदानी
    0.35
     Temporary
    0.35
     transitory
    0.35
     ego
    0.35
     lokalen
    0.34
    POSITIVE LOGITS
     coarser
    0.60
     coarse
    0.59
    粗
    0.53
     macro
    0.53
     généraux
    0.52
    macro
    0.50
     general
    0.50
     Generals
    0.50
     GENERAL
    0.50
     coarsely
    0.49
    Activations Density 0.239%

    No Known Activations