© 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
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208557
    Prev
    Next
    INDEX
    Explanations

    asking complex questions

    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_20_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
    si
    0.34
    none
    0.33
    h
    0.33
    text
    0.32
     prohibited
    0.31
    tr
    0.30
    sv
    0.30
    overline
    0.30
     ਅਤੇ
    0.30
    sl
    0.29
    POSITIVE LOGITS
     βά
    0.37
     BlogPost
    0.35
     डेंटल
    0.31
    мента
    0.30
     tutur
    0.30
    篮
    0.30
    晗
    0.30
     बग
    0.30
     ভবিষ্যতের
    0.30
     Vicki
    0.30
    Activations Density 0.032%

    No Known Activations