© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 133832
    Prev
    Next
    INDEX
    Explanations

    getting the current date

    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_37_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
     instant
    0.41
     Moment
    0.41
    Calend
    0.41
     instantaneous
    0.40
     glo
    0.39
    Erro
    0.38
     moment
    0.38
     instantaneously
    0.37
    Instant
    0.37
    喀
    0.36
    POSITIVE LOGITS
    ᔨ
    0.38
    ਦੇ
    0.37
    وار
    0.37
    distribution
    0.36
     confisc
    0.36
    ूले
    0.35
     என்றால்
    0.35
     Mansfield
    0.35
     distributing
    0.35
     germination
    0.34
    Activations Density 0.005%

    No Known Activations