© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194220
    Prev
    Next
    INDEX
    Explanations

    varied language food terms

    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_9_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
    وق
    0.51
    ं
    0.45
    resistance
    0.44
    in
    0.43
    vest
    0.42
    /**
    0.42
    when
    0.42
    平衡
    0.42
    mersive
    0.42
    m
    0.42
    POSITIVE LOGITS
     чёр
    0.62
    ёл
    0.55
     മുൻ
    0.55
     pë
    0.55
     publicized
    0.54
     grinned
    0.53
     tòa
    0.52
     ブラック
    0.52
     സി
    0.51
     giáo
    0.51
    Activations Density 0.000%

    No Known Activations