© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159064
    Prev
    Next
    INDEX
    Explanations

    words with ar/ai followed by body/box/etc

    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_2_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
    ม
    1.95
    ล
    1.63
    ת
    1.59
    ب
    1.58
    ل
    1.56
    ز
    1.55
    त
    1.52
    م
    1.52
    د
    1.50
    ব
    1.45
    POSITIVE LOGITS
    man
    0.84
    and
    0.83
     transgression
    0.83
     I
    0.82
    n
    0.81
    ien
    0.80
     insignia
    0.78
    jacking
    0.76
    artis
    0.75
     predisposition
    0.75
    Activations Density 0.000%

    No Known Activations