© 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. 259897
    Prev
    Next
    INDEX
    Explanations

    medical instructions or conditions

    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
    ጻ
    0.17
    বার্ট
    0.15
     chestnut
    0.15
    ช่วย
    0.14
     collaborateurs
    0.14
     custard
    0.14
     Онлайн
    0.14
    🧇
    0.14
     অতুল
    0.13
     хороший
    0.13
    POSITIVE LOGITS
     emit
    0.16
     effluents
    0.16
     tinnitus
    0.15
    كي
    0.15
    pecies
    0.15
    distortion
    0.14
    avax
    0.14
    قر
    0.14
    ICAS
    0.14
     accidens
    0.14
    Activations Density 0.001%

    No Known Activations