© 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. 48557
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or abbreviations

    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
     feel
    0.36
     Narr
    0.36
     Systematic
    0.36
     느
    0.34
     narr
    0.34
     Narrative
    0.34
     nim
    0.34
     array
    0.33
     petitioned
    0.32
     iteration
    0.32
    POSITIVE LOGITS
    ristmas
    0.37
    學校
    0.34
    rural
    0.34
    purecounter
    0.34
    面對
    0.33
    iftoire
    0.33
    skirts
    0.33
    rym
    0.33
    ഭ
    0.33
    lendir
    0.32
    Activations Density 0.008%

    No Known Activations