© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98928
    Prev
    Next
    INDEX
    Explanations

    want to

    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_14_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
    Ketika
    0.59
    Cuando
    0.54
    Statistics
    0.52
    ה
    0.51
    Vale
    0.49
    Когда
    0.49
    Kako
    0.49
    Porque
    0.49
    様に
    0.49
    この
    0.49
    POSITIVE LOGITS
     دو
    0.62
     पाठ्यक्रम
    0.60
     balt
    0.54
     تر
    0.52
     Applic
    0.50
     ز
    0.50
     l
    0.49
    rs
    0.48
     SCH
    0.48
     OCA
    0.47
    Activations Density 0.000%

    No Known Activations