© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139895
    Prev
    Next
    INDEX
    Explanations

    read for pleasure with discretion

    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
    ன்
    0.55
     escucha
    0.54
     creep
    0.52
     condesc
    0.52
     innovator
    0.52
     primero
    0.51
     brus
    0.51
    䚯
    0.50
    freund
    0.50
     crou
    0.50
    POSITIVE LOGITS
    Akt
    0.61
    ki
    0.59
    na
    0.59
    Na
    0.57
    Property
    0.54
    Sai
    0.54
    Income
    0.53
    പ്പെടെ
    0.53
    Forms
    0.52
    Hr
    0.52
    Activations Density 0.000%

    No Known Activations