© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 638
    Prev
    Next
    INDEX
    Explanations

    fit together

    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_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
     อนุ
    0.39
     tiring
    0.37
     отклю
    0.37
     अनु
    0.37
    嚕
    0.36
     सुर
    0.36
     сцена
    0.35
    嬪
    0.35
    पाठी
    0.34
     क्रमांक
    0.34
    POSITIVE LOGITS
     fit
    1.07
     dovet
    0.99
    Fit
    0.94
    fit
    0.91
     Fit
    0.89
     interlocking
    0.88
     fits
    0.86
     fitted
    0.85
     फिट
    0.80
    fitted
    0.79
    Activations Density 0.072%

    No Known Activations