© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248875
    Prev
    Next
    INDEX
    Explanations

    code and data methods

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     git
    0.61
     g
    0.55
     గ
    0.55
     gt
    0.55
    git
    0.54
    gt
    0.51
     गेट
    0.50
     getting
    0.48
     GED
    0.47
     Git
    0.47
    POSITIVE LOGITS
    presumably
    0.38
    我有
    0.38
    Got
    0.37
    áty
    0.37
    籵
    0.37
    십
    0.37
    isem
    0.35
    Можно
    0.35
    얄
    0.34
    Give
    0.34
    Activations Density 0.001%

    No Known Activations