© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15247
    Prev
    Next
    INDEX
    Explanations

    timestamps in scripts

    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_13_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
    ﻪ
    0.64
    если
    0.58
    }$;
    0.56
    }=
    0.55
    }${
    0.55
    심히
    0.54
     tenido
    0.54
    ット
    0.54
    ශ
    0.53
    ств
    0.53
    POSITIVE LOGITS
    in
    0.61
     scones
    0.54
     Cupid
    0.53
     that
    0.52
     chipped
    0.52
     Raspberry
    0.52
     donuts
    0.52
     breakup
    0.52
     variété
    0.51
     HTTPS
    0.50
    Activations Density 0.003%

    No Known Activations