© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61554
    Prev
    Next
    INDEX
    Explanations

    information content

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     extrémité
    0.36
    шення
    0.35
    鉭
    0.35
     subdue
    0.35
     peasantry
    0.35
     deme
    0.34
    activeIndex
    0.34
    慑
    0.34
     attiva
    0.34
    攙
    0.34
    POSITIVE LOGITS
     content
    1.43
     information
    1.21
    content
    1.20
     Content
    1.16
    内容
    1.15
    Content
    1.12
     data
    1.07
     कंटेंट
    1.06
     informações
    1.05
     información
    1.04
    Activations Density 0.029%

    No Known Activations