© 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. 2964
    Prev
    Next
    INDEX
    Explanations

    digits, numbers, 'to' followed by words

    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
     تفس
    0.37
    손
    0.37
    riot
    0.35
    뉜
    0.34
     امد
    0.34
    دون
    0.33
     oi
    0.33
     مؤس
    0.33
    Dio
    0.33
    胛
    0.33
    POSITIVE LOGITS
    ৯
    0.53
     ninety
    0.45
     ۹
    0.43
     Ninety
    0.40
    ৯০
    0.39
     ৯
    0.39
     చక్కెర
    0.39
     नाइन
    0.38
     ९
    0.38
    <0xBF>
    0.38
    Activations Density 0.028%

    No Known Activations