© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81021
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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_53_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
    赤
    0.82
     赤
    0.66
    Red
    0.57
     red
    0.55
    子
    0.54
    red
    0.53
     Red
    0.52
     子
    0.47
    child
    0.46
    ared
    0.45
    POSITIVE LOGITS
    染
    0.46
     Small
    0.46
     색
    0.42
     tiểu
    0.41
     गुण
    0.41
     Zeiss
    0.41
    Small
    0.40
     રંગ
    0.40
     nhiễm
    0.40
     Katie
    0.39
    Activations Density 0.014%

    No Known Activations