© 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. 139712
    Prev
    Next
    INDEX
    Explanations

    Al followed by log, fields, or nlp

    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
     Miller
    0.16
    '
    0.15
    ad
    0.14
     MILLER
    0.13
    Під
    0.13
    Miller
    0.13
    কে
    0.12
    اد
    0.12
     Neil
    0.12
     Lynch
    0.12
    POSITIVE LOGITS
    sax
    0.15
     Saxony
    0.13
     beetles
    0.13
     သ
    0.13
     ግራም
    0.13
     thermometers
    0.13
     sajana
    0.13
    roa
    0.13
     volcanoes
    0.13
     olives
    0.12
    Activations Density 0.003%

    No Known Activations