© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98108
    Prev
    Next
    INDEX
    Explanations

    companies and brands

    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_14_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
    ats
    0.61
    2
    0.54
    ated
    0.53
    ak
    0.52
    text
    0.52
    ↵
    0.51
    last
    0.51
    '
    0.51
    ads
    0.51
    aban
    0.51
    POSITIVE LOGITS
     mannit
    0.55
     occip
    0.51
     desider
    0.50
    कॉइन
    0.50
     insur
    0.50
     стрель
    0.49
     яе
    0.48
     मदत
    0.48
     सिंप
    0.48
     lLoginID
    0.48
    Activations Density 0.011%

    No Known Activations