© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178382
    Prev
    Next
    INDEX
    Explanations

    code definitions

    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_50_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
    bottle
    0.39
     円
    0.37
    十章
    0.37
     raindrops
    0.37
    apple
    0.36
    डोर
    0.36
    bow
    0.36
     von
    0.36
     "-
    0.34
     spheres
    0.33
    POSITIVE LOGITS
    нологи
    0.38
     Auflage
    0.38
    textvariable
    0.38
    ွဲ
    0.36
    ئت
    0.36
     laying
    0.36
    约束
    0.35
    ()].
    0.35
     တော့
    0.35
    मर्रा
    0.34
    Activations Density 0.000%

    No Known Activations