© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36183
    Prev
    Next
    INDEX
    Explanations

    TurboTax, Pascal, key

    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_3_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
    ри
    0.87
    ن
    0.86
    ور
    0.84
    ர
    0.83
    ла
    0.80
    ת
    0.79
    ub
    0.75
    os
    0.74
    ar
    0.70
    ib
    0.70
    POSITIVE LOGITS
    ↵
    0.95
     proje
    0.75
     y
    0.72
     +
    0.72
     -
    0.71
    )*
    0.70
     P
    0.70
     CO
    0.67
      
    0.66
     fabric
    0.66
    Activations Density 0.005%

    No Known Activations