© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46481
    Prev
    Next
    INDEX
    Explanations

    days off

    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_13_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
    сси
    0.57
    '
    0.50
    makeText
    0.47
    ต์
    0.46
     penc
    0.45
    рей
    0.45
     computable
    0.45
     prompt
    0.44
    .
    0.44
    ಿಗಳು
    0.43
    POSITIVE LOGITS
     Iberian
    0.52
     Aloe
    0.51
     Saleem
    0.50
     Prayers
    0.49
     Ages
    0.48
     Chloe
    0.48
     津
    0.48
     Importantly
    0.48
     Uncle
    0.47
     Ginkuhà
    0.47
    Activations Density 0.000%

    No Known Activations