© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11405
    Prev
    Next
    INDEX
    Explanations

    appropriate behavior/response/channels/genres/source/communicationlump

    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_13_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
    र
    0.28
    あなたは
    0.23
    ונים
    0.23
    ग्राम
    0.22
    src
    0.22
    เลือก
    0.22
     রাষ্ট্র
    0.22
    Ска
    0.22
    OKE
    0.22
    })
    0.21
    POSITIVE LOGITS
     व्यक्ती
    0.21
    ាត់
    0.20
     contrô
    0.20
     bhave
    0.20
     controle
    0.19
     vertebrae
    0.19
     مشتقه
    0.19
    дук
    0.19
     handels
    0.19
     interle
    0.18
    Activations Density 0.008%

    No Known Activations