© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197398
    Prev
    Next
    INDEX
    Explanations

    complex technical information

    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_50_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
     thái
    0.43
     냉
    0.40
     عف
    0.40
    TOUCH
    0.40
    Tail
    0.39
     sammeln
    0.39
     වලින්
    0.39
     tail
    0.38
     batt
    0.38
     சட்டமன்ற
    0.38
    POSITIVE LOGITS
    pé
    0.40
     sentidos
    0.40
    모
    0.39
     बीबी
    0.37
     Notification
    0.37
     способ
    0.36
     கிறிஸ்து
    0.36
     ito
    0.36
     Gour
    0.36
    CCO
    0.35
    Activations Density 0.022%

    No Known Activations