© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123930
    Prev
    Next
    INDEX
    Explanations

    Turkish words ending in 'dur' or 'sü'

    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
    f
    1.21
    to
    1.15
    j
    0.88
    nYou
    0.85
    렸
    0.82
    c
    0.79
    لي
    0.79
    ص
    0.78
    n
    0.77
     Сти
    0.75
    POSITIVE LOGITS
    -
    1.05
    ’
    0.91
    ता
    0.90
    च्या
    0.88
    ด
    0.86
    ने
    0.85
    ล
    0.84
    ის
    0.78
    во
    0.76
    ことなく
    0.75
    Activations Density 0.000%

    No Known Activations