© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18401
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     recou
    0.37
    প্প
    0.34
     Taiwanese
    0.34
    !".
    0.33
    ሸ
    0.33
     slip
    0.33
     trapped
    0.33
    ulsions
    0.33
     Backbone
    0.33
     Involvement
    0.32
    POSITIVE LOGITS
     ইন
    0.39
     разви
    0.38
    feer
    0.38
     кома
    0.38
    insol
    0.37
    cel
    0.37
     فى
    0.36
     குறித்த
    0.36
    ransfer
    0.36
    ޚ
    0.35
    Activations Density 0.010%

    No Known Activations