© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107885
    Prev
    Next
    INDEX
    Explanations

    ar/izar/azar endings

    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_1_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
    itatea
    1.22
    ους
    1.09
    ರ್‌
    1.04
    ના
    0.98
    ’
    0.97
     thatched
    0.96
     ambao
    0.96
     )}
    0.96
     aşağıdaki
    0.96
     aston
    0.94
    POSITIVE LOGITS
    ت
    2.03
    т
    1.34
    with
    1.31
    de
    1.30
    2
    1.25
    i
    1.22
    t
    1.20
    त
    1.16
    ll
    1.15
    কে
    1.13
    Activations Density 0.001%

    No Known Activations