© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57415
    Prev
    Next
    INDEX
    Explanations

    exact, Hanson, Nus

    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_11_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
     Starts
    0.48
    随着
    0.46
    错误的
    0.46
     Says
    0.46
     Defects
    0.46
     Ways
    0.45
     Wrong
    0.45
    ¨
    0.45
    ací
    0.45
    潜在
    0.45
    POSITIVE LOGITS
    </h2>
    0.55
     거래
    0.50
    of
    0.50
     remittance
    0.50
    тива
    0.49
     herbaceous
    0.49
     ingress
    0.49
     transactional
    0.48
     transaction
    0.48
     econometric
    0.46
    Activations Density 0.000%

    No Known Activations