© 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. 203842
    Prev
    Next
    INDEX
    Explanations

    programming tools

    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
    AsUpIndicator
    0.39
     मंद
    0.39
    гран
    0.38
    ㅆ
    0.37
    candidate
    0.37
     materiál
    0.35
    yse
    0.35
    막
    0.35
    kreuz
    0.34
    atemala
    0.34
    POSITIVE LOGITS
     Tool
    0.38
    ̸
    0.36
    YYYY
    0.36
     tool
    0.36
     TDs
    0.36
    NORE
    0.35
     lunches
    0.35
     Terrace
    0.35
     راجس
    0.35
     প্ল্যাট
    0.35
    Activations Density 0.001%

    No Known Activations