© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120868
    Prev
    Next
    INDEX
    Explanations

    russian male and female names

    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_27_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
     betekent
    0.42
    neq
    0.38
    vio
    0.38
    strictly
    0.38
    ń
    0.38
    ƒ
    0.37
     يعني
    0.37
    luc
    0.36
    嬸
    0.36
    irao
    0.36
    POSITIVE LOGITS
     Μαρ
    0.43
     помі
    0.42
    າມາດ
    0.41
    ্‌
    0.39
    IDTH
    0.39
     ಕನ
    0.39
    Dt
    0.37
     quais
    0.37
    Benzoimidazol
    0.37
    ິດຕ
    0.37
    Activations Density 0.000%

    No Known Activations