© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42611
    Prev
    Next
    INDEX
    Explanations

    file uploads and multipart parts

    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_3_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
    st
    0.80
    ม
    0.77
    with
    0.76
    Data
    0.74
    ts
    0.73
    sk
    0.72
    timestamp
    0.71
    r
    0.71
    lar
    0.71
    sh
    0.69
    POSITIVE LOGITS
     advocates
    0.77
    ли
    0.73
    сторон
    0.71
     chats
    0.69
     evas
    0.67
    ophylline
    0.67
    вость
    0.66
    amı
    0.66
     afirmou
    0.66
     afirmó
    0.66
    Activations Density 0.006%

    No Known Activations