© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217273
    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_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
    ໂ
    0.40
    Dess
    0.39
     composto
    0.38
     composed
    0.36
     পার্টি
    0.36
    FIT
    0.36
    يرات
    0.35
    成員
    0.35
     रच
    0.35
    ࿐
    0.35
    POSITIVE LOGITS
    uu
    0.41
     rightly
    0.39
    abling
    0.38
    getKeyCode
    0.38
     smile
    0.37
    duled
    0.35
    Slf
    0.35
     aaa
    0.35
    ﷲ
    0.35
     Enable
    0.35
    Activations Density 0.001%

    No Known Activations