© 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-3-27B-IT
    3. 55-GEMMASCOPE-2-TRANSCODER-262K
    4. 51665
    Prev
    Next
    INDEX
    Explanations

    say async

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    ⵅ
    0.39
     चाहिये
    0.38
     Hearing
    0.37
    மோ
    0.37
    Chairman
    0.37
     ---
    0.37
     রোগের
    0.36
    生气
    0.36
    тове
    0.35
     #####
    0.35
    POSITIVE LOGITS
     munt
    0.39
     తన
    0.37
     directe
    0.35
    ложении
    0.34
    绶
    0.34
    ()=>{
    0.33
    ware
    0.33
     prenda
    0.33
    盪
    0.33
    exhaustive
    0.33
    Activations Density 0.001%

    No Known Activations