© 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. 247952
    Prev
    Next
    INDEX
    Explanations

    ever

    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
     E
    0.64
    constant
    0.54
     ई
    0.52
     constant
    0.48
    E
    0.46
     constante
    0.44
    Constant
    0.40
     konstant
    0.38
    ־
    0.38
    const
    0.38
    POSITIVE LOGITS
     changes
    0.72
     Changes
    0.69
    Changes
    0.63
    changes
    0.62
     Änderungen
    0.57
     चेंजेस
    0.55
     cambios
    0.54
     изменения
    0.54
     perubahan
    0.54
     Change
    0.51
    Activations Density 0.001%

    No Known Activations