© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125868
    Prev
    Next
    INDEX
    Explanations

    history.com/news/

    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_37_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
     oral
    2.13
     Oral
    1.97
    Oral
    1.87
     orally
    1.52
     orale
    1.52
    oral
    1.48
     मौखिक
    1.30
    口
    1.12
    口腔
    1.05
     口
    1.00
    POSITIVE LOGITS
    DAR
    0.40
    ढी
    0.35
     squad
    0.34
     commanders
    0.34
    缰
    0.34
    CSC
    0.34
     flanks
    0.34
    凶
    0.33
     DAR
    0.33
    Pel
    0.33
    Activations Density 0.005%

    No Known Activations