© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43500
    Prev
    Next
    INDEX
    Explanations

    preceding a noun

    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_22_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
    lui
    0.15
     Nearly
    0.15
     ಹೊಂದಿದೆ
    0.15
     Featuring
    0.14
     ष
    0.14
     permettant
    0.14
     제공
    0.13
    ществует
    0.13
     Leveraging
    0.13
    iff
    0.13
    POSITIVE LOGITS
    今後の
    0.14
    ໜ
    0.13
    蛞
    0.13
     screwed
    0.13
    大战
    0.13
    别人
    0.12
     tranquill
    0.12
     महत्त्व
    0.12
    Uniform
    0.12
    将来
    0.12
    Activations Density 0.039%

    No Known Activations