© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209503
    Prev
    Next
    INDEX
    Explanations

    geometry

    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_10_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
    ก
    0.82
     geometric
    0.82
     two
    0.75
     maze
    0.75
     testamentary
    0.75
     geometry
    0.73
     geomet
    0.73
     ofrec
    0.71
     rover
    0.71
                  
    0.70
    POSITIVE LOGITS
    in
    1.47
    de
    1.41
    f
    1.07
    1
    0.96
    re
    0.94
    t
    0.93
    se
    0.92
    di
    0.92
    ti
    0.90
    st
    0.90
    Activations Density 0.004%

    No Known Activations