© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245970
    Prev
    Next
    INDEX
    Explanations

    command descriptions and arguments

    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_40_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
    Rip
    0.43
    瀬
    0.39
     Full
    0.38
     అమ
    0.38
     chestnut
    0.38
    Full
    0.37
     Amr
    0.37
    Stars
    0.35
     集
    0.35
    sur
    0.35
    POSITIVE LOGITS
     кух
    0.37
    াচ্ছে
    0.37
    CallbackContext
    0.37
    给予
    0.35
     colère
    0.35
    winfx
    0.35
     бра
    0.35
    %">
    0.35
    ଈ
    0.35
    ttt
    0.34
    Activations Density 0.000%

    No Known Activations