© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203130
    Prev
    Next
    INDEX
    Explanations

    non-Latin characters

    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
    傅
    0.40
    textAppearance
    0.37
    FU
    0.36
    modelVersion
    0.36
    蛋白
    0.35
     begrip
    0.35
     冖
    0.35
     Relevant
    0.34
     inwon
    0.34
    cutter
    0.34
    POSITIVE LOGITS
     花
    0.40
     avoid
    0.39
    asos
    0.39
     kasus
    0.39
    避
    0.38
     just
    0.38
     mutually
    0.38
    лади
    0.38
    花
    0.38
     fracturing
    0.37
    Activations Density 0.000%

    No Known Activations