© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 201117
    Prev
    Next
    INDEX
    Explanations

    framework, code components, files, or complications

    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
    B
    0.69
    Camp
    0.52
    After
    0.51
    위
    0.51
    Living
    0.50
    지는
    0.50
    F
    0.50
    糸
    0.50
    Dance
    0.49
    Rent
    0.49
    POSITIVE LOGITS
     Koch
    0.61
     د
    0.59
     восстанов
    0.59
     পদক্ষেপ
    0.58
     ста
    0.57
     wohl
    0.56
     koch
    0.55
     ку
    0.55
     had
    0.54
    asil
    0.54
    Activations Density 0.001%

    No Known Activations