© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199822
    Prev
    Next
    INDEX
    Explanations

    medical conditions and pain descriptors

    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_15_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
    </h4>
    0.66
     erroneous
    0.61
     образова
    0.54
     важ
    0.54
     наро
    0.54
     estudiante
    0.52
    </th>
    0.52
     образования
    0.51
     InnoDB
    0.51
    ﾁ
    0.51
    POSITIVE LOGITS
    Arts
    0.54
     gels
    0.50
    Philip
    0.50
    Bats
    0.49
     Arts
    0.49
    Architect
    0.49
    Ryan
    0.49
    Wallace
    0.49
    Wall
    0.48
    Music
    0.48
    Activations Density 0.001%

    No Known Activations