© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199011
    Prev
    Next
    INDEX
    Explanations

    code comments and separators

    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_27_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
     Broadcasting
    0.32
    这才
    0.32
     说明
    0.31
     shouldUse
    0.30
    芾
    0.30
     ਸਾ
    0.29
     forKey
    0.29
    IDING
    0.28
     chatting
    0.28
    彈
    0.28
    POSITIVE LOGITS
     grunn
    0.32
     fleste
    0.32
    teenth
    0.32
    دو
    0.31
     homogen
    0.30
     прив
    0.30
    深深
    0.30
    otrophic
    0.29
     mito
    0.29
     impermeable
    0.29
    Activations Density 0.000%

    No Known Activations