© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196148
    Prev
    Next
    INDEX
    Explanations

    python code imports

    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_46_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
     Missionary
    0.40
     Localization
    0.37
     Gallo
    0.37
    discrimination
    0.36
     추
    0.36
     uncorrelated
    0.35
     modeling
    0.34
    ベージュ
    0.34
     fallback
    0.34
    ͗
    0.34
    POSITIVE LOGITS
    IDES
    0.41
    antically
    0.37
    蚌
    0.37
     Winf
    0.37
    lands
    0.36
    ainted
    0.36
     जलन
    0.36
     बिट
    0.36
    ծ
    0.36
    Spent
    0.35
    Activations Density 0.000%

    No Known Activations