© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206874
    Prev
    Next
    INDEX
    Explanations

    foreign words and symbols

    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
    ZY
    0.39
    ’
    0.38
    PosZ
    0.37
    Í
    0.37
    ureen
    0.36
    Forecast
    0.35
    NOT
    0.35
    Config
    0.34
    GPT
    0.34
    WITH
    0.34
    POSITIVE LOGITS
     további
    0.38
     ሁለት
    0.37
     mathematicians
    0.36
     입력
    0.35
    สอง
    0.35
    राधिक
    0.35
     doubling
    0.35
     મહિલા
    0.35
    啰
    0.34
     మ్యాచ్
    0.34
    Activations Density 0.001%

    No Known Activations