© 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. 50861
    Prev
    Next
    INDEX
    Explanations

    cool, stylish, edgy

    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
     गोला
    0.41
     Bier
    0.40
     рынок
    0.39
    椒
    0.39
     LW
    0.38
     Horror
    0.38
    𒀸
    0.38
    iacute
    0.38
    Tapi
    0.38
     Ort
    0.37
    POSITIVE LOGITS
    かっこ
    0.66
     swagger
    0.65
     멋
    0.65
    멋
    0.63
     cool
    0.62
     glamorous
    0.61
     badass
    0.56
    カッコ
    0.56
    cool
    0.55
     dashing
    0.55
    Activations Density 0.101%

    No Known Activations