© 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. 14018
    Prev
    Next
    INDEX
    Explanations

    numbers and days

    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
     १००
    0.44
     ১০০
    0.41
    सनीय
    0.38
     calci
    0.37
     BLACK
    0.36
     десять
    0.35
    件
    0.35
    正常
    0.35
     Ten
    0.34
    衣服
    0.34
    POSITIVE LOGITS
     Aunt
    0.73
    Tuesday
    0.72
     Tuesdays
    0.71
     seventeen
    0.69
     Tuesday
    0.66
     seventeenth
    0.66
     aunts
    0.62
    
    0.61
     séptimo
    0.61
     १७
    0.60
    Activations Density 0.145%

    No Known Activations