© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159849
    Prev
    Next
    INDEX
    Explanations

    non-latin characters

    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_2_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
    ف
    1.43
    ak
    1.33
    ิ
    1.28
    ומי
    1.20
    ா
    1.19
    at
    1.17
    os
    1.15
    ാ
    1.15
    ا
    1.11
    ına
    1.09
    POSITIVE LOGITS
    は
    1.60
    是
    1.44
    Т
    1.38
    О
    1.32
     that
    1.30
     is
    1.27
    Те
    1.27
    리
    1.27
    일
    1.26
    При
    1.22
    Activations Density 0.000%

    No Known Activations