© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35457
    Prev
    Next
    INDEX
    Explanations

    listing things

    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_11_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
     ម
    0.61
    ParamList
    0.57
    Dichloro
    0.56
     أساس
    0.56
     éxitos
    0.55
    ابة
    0.54
     anuncios
    0.54
    坷
    0.54
    妗
    0.54
     eléctrica
    0.52
    POSITIVE LOGITS
    ’
    0.79
    uk
    0.59
    ug
    0.57
    ิ
    0.57
    ot
    0.56
    าย
    0.55
     tanpa
    0.54
    ึ
    0.54
     The
    0.54
    yn
    0.54
    Activations Density 0.015%

    No Known Activations