© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209413
    Prev
    Next
    INDEX
    Explanations

    lists and resources

    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_10_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
    ان
    0.54
    ian
    0.46
    p
    0.45
    an
    0.39
    ina
    0.39
    чая
    0.38
     can
    0.37
    ى
    0.37
     It
    0.36
    ਬ
    0.34
    POSITIVE LOGITS
    zości
    0.42
    ’).
    0.41
    ‌ನ
    0.41
    著名的
    0.40
    ’)
    0.39
     păr
    0.39
    ’),
    0.39
     CVD
    0.39
    oes
    0.39
    ❷
    0.38
    Activations Density 0.064%

    No Known Activations