© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213668
    Prev
    Next
    INDEX
    Explanations

    compiled program

    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_5_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
    in
    1.39
    ad
    1.20
    it
    1.15
    ne
    1.09
    ار
    1.08
    ב
    1.08
    w
    1.03
     the
    1.02
    the
    1.02
    ul
    1.02
    POSITIVE LOGITS
    0.99
     Técn
    0.95
    لي
    0.87
    ሳሪያ
    0.87
    יות
    0.85
    ﺭ
    0.84
    том
    0.82
    ಬ್ಬಿಣ
    0.81
    ας
    0.77
    مثل
    0.77
    Activations Density 0.001%

    No Known Activations