© 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. 18478
    Prev
    Next
    INDEX
    Explanations

    webdriver

    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
     VAS
    0.39
    abayashi
    0.38
    ψη
    0.36
    墺
    0.36
     భాగంగా
    0.35
    帀
    0.35
     Yu
    0.34
    orini
    0.34
    <^
    0.34
    澳大利亚
    0.34
    POSITIVE LOGITS
     wait
    0.66
    wait
    0.64
    waiting
    0.59
     Wait
    0.57
     waiting
    0.54
     기다
    0.53
     testing
    0.52
    等待
    0.52
     WAIT
    0.52
     waited
    0.51
    Activations Density 0.001%

    No Known Activations