© 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. 142873
    Prev
    Next
    INDEX
    Explanations

    Russian "ме" followed by 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_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
    ма
    1.52
    де
    1.45
    ،
    1.40
    م
    1.38
    し
    1.38
    ā
    1.27
    m
    1.20
    ación
    1.19
    म
    1.16
    आई
    1.16
    POSITIVE LOGITS
    ت
    1.63
    ون
    1.38
    Z
    1.31
    т
    1.26
    是
    1.18
    一
    1.16
     is
    1.15
    U
    1.12
    MI
    1.11
    ال
    1.10
    Activations Density 0.000%

    No Known Activations