© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205936
    Prev
    Next
    INDEX
    Explanations

    what you've already tried

    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_37_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
     вывести
    0.40
     обладают
    0.39
     ContentView
    0.38
     содержание
    0.38
     Catawiki
    0.37
     contenido
    0.36
    蒿
    0.35
     concede
    0.35
    Vamos
    0.35
     содержимое
    0.35
    POSITIVE LOGITS
    }_{+}\
    0.42
     geçen
    0.42
    アス
    0.38
    我想
    0.38
     ασ
    0.38
    وصل
    0.37
     asylum
    0.37
     organelles
    0.37
     শিক্ষকদের
    0.37
     strukt
    0.36
    Activations Density 0.001%

    No Known Activations