© 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. 171102
    Prev
    Next
    INDEX
    Explanations

    formatting characters

    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
    Negative Logits
    also
    0.50
    Also
    0.49
     also
    0.49
    available
    0.43
    unavailable
    0.43
     ignores
    0.41
     available
    0.41
     cũng
    0.40
    也可以
    0.40
    也
    0.40
    POSITIVE LOGITS
     (<
    0.88
     ww
    0.82
     ([
    0.77
    ww
    0.70
     <
    0.69
     (\
    0.65
    (<
    0.64
     htt
    0.63
     (/
    0.61
     [\
    0.61
    Activations Density 0.003%

    No Known Activations