© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89557
    Prev
    Next
    INDEX
    Explanations

    pip install

    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_23_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
    goài
    0.43
    ቐ
    0.43
    ლებიც
    0.42
    ("|"+"
    0.41
    ұл
    0.41
    ޖ
    0.41
    ційних
    0.41
    Offering
    0.40
     тренер
    0.40
    льт
    0.39
    POSITIVE LOGITS
     bande
    0.38
     Yaw
    0.37
     =
    0.34
     Bande
    0.34
     Parton
    0.34
     Difference
    0.33
     판
    0.33
     DIFF
    0.33
     differs
    0.32
     مگر
    0.32
    Activations Density 0.012%

    No Known Activations