© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 140828
    Prev
    Next
    INDEX
    Explanations

    AI models

    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
    動
    0.28
    综合
    0.26
    (!)
    0.26
    采取
    0.26
     declared
    0.25
     zdrav
    0.25
    (_,
    0.25
     movable
    0.25
    </s>
    0.24
    asah
    0.24
    POSITIVE LOGITS
     caza
    0.32
     Voit
    0.32
    Wouldn
    0.31
     eigenes
    0.31
    レシ
    0.30
     ؛
    0.30
     বলেই
    0.30
    年モデル
    0.30
     சென்ன
    0.29
    adura
    0.29
    Activations Density 0.003%

    No Known Activations