© 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. 9204
    Prev
    Next
    INDEX
    Explanations

    surgical procedures

    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
     송
    0.51
    ka
    0.50
    ж
    0.49
    oing
    0.48
    вку
    0.47
    handlung
    0.45
     جور
    0.45
    ुलिस
    0.44
    aji
    0.44
    iend
    0.44
    POSITIVE LOGITS
     cardiology
    0.52
    }\
    0.51
    臨床
    0.51
     pyruvate
    0.51
     Rafa
    0.49
     Cardiology
    0.49
    </strong>
    0.49
     desta
    0.49
    irectional
    0.48
     aorta
    0.48
    Activations Density 0.022%

    No Known Activations