© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122543
    Prev
    Next
    INDEX
    Explanations

    multilingual words or phrases

    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_3_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
     работы
    0.80
     práce
    0.78
    งาน
    0.65
     работе
    0.65
    riot
    0.63
    ’
    0.63
    ET
    0.62
     работать
    0.60
    destroy
    0.59
    仕事
    0.58
    POSITIVE LOGITS
    ت
    0.84
    ى
    0.81
    ные
    0.76
    ת
    0.74
    ного
    0.66
    ный
    0.66
    ا
    0.65
    j
    0.64
    కు
    0.63
    았
    0.63
    Activations Density 0.001%

    No Known Activations