© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 2903
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
     Хоро
    0.53
    јединачна
    0.50
     Потом
    0.50
     Kız
    0.49
     koje
    0.49
    سال
    0.48
     {\
    0.48
    ્ર
    0.47
     Gson
    0.47
     По
    0.47
    POSITIVE LOGITS
    en
    0.82
    albeit
    0.73
    e
    0.66
     albeit
    0.63
     previstas
    0.61
    <0x8F>
    0.60
    疫情防控
    0.58
    짬
    0.58
    ку
    0.57
    ﻪ
    0.57
    Activations Density 0.001%

    No Known Activations