© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63332
    Prev
    Next
    INDEX
    Explanations

    history

    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_46_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
    historic
    0.46
     historic
    0.41
     Historic
    0.41
    Historic
    0.40
     엘
    0.39
    site
    0.38
     CSV
    0.37
     CEC
    0.36
    saga
    0.36
    <0x9D>
    0.36
    POSITIVE LOGITS
    _="
    0.43
    اتے
    0.40
    经验
    0.39
     buon
    0.39
     Logical
    0.39
    cznej
    0.39
     textbook
    0.38
    ionalità
    0.38
    риа
    0.38
     fapt
    0.38
    Activations Density 0.003%

    No Known Activations