© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44683
    Prev
    Next
    INDEX
    Explanations

    in the presence of or context 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_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
    嶅
    0.19
     methacrylate
    0.17
    委員會
    0.17
    嶈
    0.17
    อย่างไร
    0.17
    ików
    0.17
    osphère
    0.17
     কেবল
    0.17
    যখন
    0.16
    ⾼
    0.16
    POSITIVE LOGITS
     loan
    0.17
    fusc
    0.16
     Realm
    0.16
     Besitz
    0.15
     Loan
    0.15
     Pray
    0.15
    borrow
    0.15
     Purchase
    0.15
     _:
    0.15
     Validate
    0.15
    Activations Density 0.017%

    No Known Activations