© 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. 14597
    Prev
    Next
    INDEX
    Explanations

    eager

    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
    د
    0.59
    д
    0.56
    ก
    0.53
    ढा
    0.52
    ड्रा
    0.50
    ش
    0.50
    证券
    0.50
    }}{\
    0.49
    doa
    0.49
    節
    0.48
    POSITIVE LOGITS
     পানি
    0.59
     देखने
    0.58
     మొదటి
    0.57
     desirous
    0.57
     પ્રથમ
    0.54
    㓞
    0.54
     solicitar
    0.54
     první
    0.54
     corrupción
    0.53
     Запад
    0.53
    Activations Density 0.035%

    No Known Activations