© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84326
    Prev
    Next
    INDEX
    Explanations

    Russian characters `м`, `х`, `Р`, `Н`

    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
    在
    1.56
    ED
    1.38
     in
    1.37
    एस
    1.35
    {
    1.34
    ك
    1.34
    리
    1.31
    \
    1.25
    的
    1.23
    కు
    1.22
    POSITIVE LOGITS
    ۰
    1.56
    ר
    1.46
    1.35
     ی
    1.34
     can
    1.31
    ر
    1.28
     $\
    1.21
    ﯼ
    1.20
    ०
    1.18
     \
    1.15
    Activations Density 0.000%

    No Known Activations