© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205604
    Prev
    Next
    INDEX
    Explanations

    sed and regex replacement

    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_37_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
     ellipsis
    0.40
     बाइ
    0.39
     Anon
    0.37
     redund
    0.37
    販
    0.37
     স্ব
    0.37
     LEM
    0.37
     કોઈપણ
    0.37
     Livraison
    0.36
    egraphics
    0.36
    POSITIVE LOGITS
     глоба
    0.48
     globales
    0.41
     global
    0.40
    全球
    0.39
    global
    0.39
     글로벌
    0.37
     glob
    0.37
     वैश्विक
    0.37
    グ
    0.36
    ﹔
    0.36
    Activations Density 0.001%

    No Known Activations