© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112142
    Prev
    Next
    INDEX
    Explanations

    Russian/Polish "ż" and "cha" prefixes

    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
    pt
    1.27
    in
    1.11
    ak
    1.06
    $
    1.06
    it
    1.04
    use
    1.04
    uk
    1.01
    ARE
    0.98
    i
    0.98
    EK
    0.93
    POSITIVE LOGITS
    ри
    1.39
    ки
    1.33
    يمان
    1.27
    ли
    1.23
    ка
    1.20
    ى
    1.16
    т
    1.15
    ку
    1.11
    ت
    1.11
    ため
    1.10
    Activations Density 0.000%

    No Known Activations