© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 81437
    Prev
    Next
    INDEX
    Explanations

    Turkish and Russian words for "inside" and "thick"

    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
    ים
    2.28
    ς
    2.05
    ों
    1.87
    s
    1.79
    ות
    1.72
    ر
    1.70
    ی
    1.70
    ओं
    1.53
    ের
    1.47
    ล
    1.46
    POSITIVE LOGITS
    c
    1.54
    ية
    1.34
    一些
    1.24
    n
    1.24
    a
    1.20
    va
    1.19
    f
    1.18
    ك
    1.17
     a
    1.16
    ように
    1.13
    Activations Density 0.000%

    No Known Activations