© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44819
    Prev
    Next
    INDEX
    Explanations

    even / даже

    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_13_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
    よく
    0.54
     elbows
    0.54
     \
    0.52
    ő
    0.52
     từ
    0.51
     elbow
    0.50
     Tells
    0.50
    บอก
    0.50
     dello
    0.49
     tasks
    0.49
    POSITIVE LOGITS
    et
    0.67
    fear
    0.60
    Coref
    0.59
    ᆨ
    0.59
    мы
    0.59
    plated
    0.59
    score
    0.58
    proyecto
    0.57
    destroy
    0.55
    ᆯ
    0.55
    Activations Density 0.000%

    No Known Activations