© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38530
    Prev
    Next
    INDEX
    Explanations

    set index

    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_11_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
     Jiménez
    0.51
    1
    0.50
     መድሃኒ
    0.49
     SVG
    0.49
     नारायण
    0.47
     ሽፋ
    0.47
    sehen
    0.46
     न्यायालया
    0.46
    oló
    0.46
    卷
    0.46
    POSITIVE LOGITS
     ajustes
    0.61
     multitud
    0.54
     toning
    0.54
    ی
    0.53
     parceria
    0.52
     rumores
    0.51
     diversa
    0.50
     processed
    0.49
    prosperity
    0.48
    ۹
    0.48
    Activations Density 0.000%

    No Known Activations