© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50897
    Prev
    Next
    INDEX
    Explanations

    wars and revolutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    ardy
    0.35
    ப்பிய
    0.32
    الب
    0.31
     benign
    0.30
    ন্দের
    0.29
    Lond
    0.29
    ľad
    0.29
    瑙
    0.29
    atomy
    0.28
    à
    0.28
    POSITIVE LOGITS
    同行
    0.41
     recollection
    0.36
     переза
    0.35
    Genre
    0.34
     TextEditing
    0.33
     Genres
    0.33
     السيارة
    0.33
     reloc
    0.32
    的变化
    0.32
     হইলে
    0.32
    Activations Density 0.009%

    No Known Activations