© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145462
    Prev
    Next
    INDEX
    Explanations

    departure from

    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_0_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
    a
    1.91
    5
    1.64
    r
    1.55
    t
    1.47
    4
    1.37
    inan
    1.35
    ۵
    1.34
    cents
    1.33
     взгля
    1.30
    and
    1.27
    POSITIVE LOGITS
    ش
    1.92
    د
    1.91
    م
    1.88
    д
    1.87
    м
    1.86
    ש
    1.70
    ز
    1.63
    на
    1.55
    س
    1.52
    ன்
    1.51
    Activations Density 0.001%

    No Known Activations