© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35040
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    คา
    0.35
    XD
    0.34
    Scorch
    0.34
    $:
    0.34
     Makeup
    0.34
    ANDE
    0.34
     अधिकारी
    0.33
     década
    0.33
    uca
    0.33
    ționale
    0.33
    POSITIVE LOGITS
    𝙞
    0.38
    簱
    0.36
    sit
    0.36
     brain
    0.35
     universal
    0.35
     eerst
    0.34
     conviction
    0.33
    Ⲟ
    0.33
     engagement
    0.33
     pyramids
    0.33
    Activations Density 0.000%

    No Known Activations