© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208838
    Prev
    Next
    INDEX
    Explanations

    summarise

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     `--
    0.46
     耳
    0.42
     साधारण
    0.42
     主
    0.41
    ainer
    0.40
     america
    0.40
    --
    0.40
    ．
    0.39
    主
    0.39
     chinese
    0.39
    POSITIVE LOGITS
     GCSE
    0.72
     pubs
    0.70
     Yorkshire
    0.68
     Norwich
    0.68
     BBC
    0.67
     Lancashire
    0.66
    BBC
    0.64
     NHS
    0.63
     Wolverhampton
    0.62
     pub
    0.61
    Activations Density 0.002%

    No Known Activations