© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132762
    Prev
    Next
    INDEX
    Explanations

    lee, li, lo, lit 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_1_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
    ↵↵
    1.60
    6
    1.35
    是
    1.34
    is
    1.31
    1
    1.31
    i
    1.30
    3
    1.26
    9
    1.23
    ing
    1.20
    ي
    1.20
    POSITIVE LOGITS
    ine
    1.02
    ”،
    0.98
    ки
    0.93
    ى
    0.91
    ());
    0.85
    ۰
    0.85
    uts
    0.85
     (‘
    0.84
    ’,
    0.84
    Translatef
    0.84
    Activations Density 0.000%

    No Known Activations