© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209504
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    imaging
    0.49
     പാർ
    0.47
     imaging
    0.46
    жня
    0.44
    桫
    0.44
     ज़र
    0.43
    ̊
    0.42
     placeholders
    0.42
    圖像
    0.42
     کاشت
    0.42
    POSITIVE LOGITS
    𝑪
    0.45
    oners
    0.44
    mation
    0.44
     شاه
    0.42
    Already
    0.41
    ming
    0.41
    高兴
    0.41
    minent
    0.40
    u
    0.40
    s
    0.39
    Activations Density 0.000%

    No Known Activations