© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 200123
    Prev
    Next
    INDEX
    Explanations

    bot, spiders, response, access

    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_15_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    體
    0.57
     unlaw
    0.48
    फ्र
    0.48
    好的
    0.48
    }$,
    0.46
    मिट
    0.45
    مول
    0.44
    偉
    0.43
     عراق
    0.43
    법
    0.43
    POSITIVE LOGITS
     Sains
    0.53
     SGS
    0.51
     P
    0.50
    z
    0.49
     Pol
    0.48
     Marker
    0.48
     Marlborough
    0.48
    a
    0.48
     M
    0.47
    elle
    0.47
    Activations Density 0.000%

    No Known Activations