© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86789
    Prev
    Next
    INDEX
    Explanations

    Southern Poverty Law Center

    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_3_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
    다라고
    0.57
    rencies
    0.55
    תן
    0.55
    '
    0.55
     август
    0.55
    IEF
    0.54
    kta
    0.54
    OUS
    0.53
    vious
    0.51
    erton
    0.50
    POSITIVE LOGITS
    C
    0.79
    、
    0.77
    Ч
    0.73
    ،
    0.71
    ט
    0.68
    רו
    0.65
    м
    0.64
    site
    0.64
    sun
    0.63
    ।
    0.63
    Activations Density 0.001%

    No Known Activations