© 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. 9012
    Prev
    Next
    INDEX
    Explanations

    numbers and "hundred"

    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
     অধি
    0.40
     Wyatt
    0.39
    ରା
    0.38
     sixteen
    0.37
    Writes
    0.37
    ாம
    0.36
    ামীর
    0.36
     吴
    0.36
     Raw
    0.34
     अधि
    0.34
    POSITIVE LOGITS
     hundred
    0.92
    hundred
    0.91
     Hundred
    0.88
     hundreds
    0.86
    Hundred
    0.86
     ৩০০
    0.82
     ৪০০
    0.81
    百
    0.78
     १००
    0.75
     hund
    0.75
    Activations Density 0.058%

    No Known Activations