© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90349
    Prev
    Next
    INDEX
    Explanations

    dynasty, Huo, transactions

    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_3_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
     que
    0.80
     hombre
    0.66
    는
    0.66
     proposito
    0.63
    ที่
    0.63
     কিন্তু
    0.62
    に
    0.62
     box
    0.61
     și
    0.61
     acest
    0.60
    POSITIVE LOGITS
    n
    1.30
    dı
    1.05
    f
    1.02
    dh
    0.99
    an
    0.92
    d
    0.90
    a
    0.88
    g
    0.88
    k
    0.88
    ad
    0.86
    Activations Density 0.000%

    No Known Activations