© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13243
    Prev
    Next
    INDEX
    Explanations

    bogged down in details

    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_13_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
     Hines
    0.50
     confortable
    0.49
    ᛁ
    0.49
    壷
    0.48
     coincide
    0.48
     Hilda
    0.48
     Rhonda
    0.48
    ()\
    0.48
     सच्ची
    0.47
     Rudi
    0.47
    POSITIVE LOGITS
    sh
    0.68
    uasion
    0.54
    un
    0.52
    ografía
    0.52
    isión
    0.51
    ución
    0.50
    수
    0.50
    메
    0.49
    шению
    0.49
    شرات
    0.49
    Activations Density 0.106%

    No Known Activations