© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90243
    Prev
    Next
    INDEX
    Explanations

    say "accented characters"

    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_60_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
    u
    0.51
    ي
    0.44
    ט
    0.43
    أي
    0.42
    ələ
    0.42
    ক
    0.41
    cía
    0.41
    __'
    0.41
    énom
    0.41
    żu
    0.41
    POSITIVE LOGITS
    ्
    0.49
    ന്തപു
    0.46
    ı
    0.45
    ๋
    0.45
    ä
    0.44
    ē
    0.44
     é
    0.43
    cardia
    0.42
    í
    0.42
    ī
    0.42
    Activations Density 0.003%

    No Known Activations