© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194395
    Prev
    Next
    INDEX
    Explanations

    pupil related words

    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_4_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
    t
    1.84
    l
    1.25
    a
    1.18
    i
    1.10
    רי
    1.08
    る
    1.08
    ת
    1.07
    ت
    1.02
    that
    1.00
    d
    1.00
    POSITIVE LOGITS
    த்தில்
    0.86
     mình
    0.83
     elke
    0.82
    ى
    0.81
     více
    0.79
    لي
    0.79
     pupils
    0.79
    辏
    0.79
     окно
    0.78
     amazed
    0.77
    Activations Density 0.001%

    No Known Activations