© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83359
    Prev
    Next
    INDEX
    Explanations

    C++ class definitions

    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_29_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
    才知道
    0.40
     Failing
    0.39
    vskip
    0.38
    arın
    0.38
     ثابت
    0.38
     तला
    0.38
     presiding
    0.37
    睑
    0.37
     aussitôt
    0.36
     Kees
    0.36
    POSITIVE LOGITS
    HAL
    0.42
     محد
    0.39
    hun
    0.37
     explos
    0.37
     unlimited
    0.37
    โดย
    0.36
    อัน
    0.36
     الش
    0.36
    OUR
    0.36
     HAL
    0.36
    Activations Density 0.001%

    No Known Activations