© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45835
    Prev
    Next
    INDEX
    Explanations

    conda activate

    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
     risposta
    0.52
     прогнозы
    0.51
     respuesta
    0.48
     與
    0.47
     versões
    0.47
     năm
    0.46
    Steady
    0.46
     resposta
    0.46
     版本
    0.45
     سمت
    0.44
    POSITIVE LOGITS
     XVII
    0.54
    ного
    0.51
     বিখ্যাত
    0.50
     XVIII
    0.50
     advocacy
    0.48
     wasteful
    0.48
     trillion
    0.48
     rupees
    0.47
    뀐
    0.47
    maal
    0.47
    Activations Density 0.003%

    No Known Activations