© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141054
    Prev
    Next
    INDEX
    Explanations

    info and new entities

    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_12_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
    b
    0.57
    on
    0.56
    os
    0.52
    because
    0.52
    medical
    0.52
    care
    0.50
    bed
    0.49
    an
    0.49
    cd
    0.48
    s
    0.48
    POSITIVE LOGITS
     LAMP
    0.58
     pesquisas
    0.57
     Aten
    0.52
     Saras
    0.52
     sard
    0.51
    試し
    0.51
    맞
    0.51
     ARIMA
    0.51
     spinor
    0.50
     exif
    0.50
    Activations Density 0.037%

    No Known Activations