© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36694
    Prev
    Next
    INDEX
    Explanations

    time evolution

    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_11_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
    s
    0.31
     he
    0.30
     All
    0.27
    ל
    0.27
    ص
    0.26
     any
    0.25
     or
    0.25
    any
    0.25
    c
    0.24
    ка
    0.24
    POSITIVE LOGITS
     মন্দির
    0.23
    팠
    0.23
     방향
    0.22
    ﺭ
    0.22
    Imagen
    0.22
    Coluna
    0.22
     pelajaran
    0.22
     الجلد
    0.22
     বাড়ী
    0.22
    )।
    0.21
    Activations Density 0.012%

    No Known Activations