© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170793
    Prev
    Next
    INDEX
    Explanations

    stay ahead of

    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_20_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
     ریس
    0.47
     D
    0.45
    检测
    0.45
    ดี
    0.45
     управления
    0.45
     வாய்
    0.43
    iris
    0.42
    E
    0.42
     опти
    0.42
    运行时
    0.42
    POSITIVE LOGITS
    结点
    0.51
     concatenated
    0.48
    BuildAction
    0.47
     homologs
    0.46
     cuarta
    0.46
     alquiler
    0.46
    subplot
    0.46
     knotted
    0.45
    🔩
    0.45
     stoichiometric
    0.45
    Activations Density 0.001%

    No Known Activations