© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9232
    Prev
    Next
    INDEX
    Explanations

    angular `@core` imports

    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
    凯
    0.42
     raus
    0.39
     وقع
    0.37
    seqNum
    0.36
    僥
    0.36
    当て
    0.36
    قع
    0.35
    achable
    0.35
    htim
    0.35
    摹
    0.35
    POSITIVE LOGITS
    View
    0.74
    view
    0.66
     View
    0.66
     view
    0.62
     query
    0.52
     VIEW
    0.51
     Element
    0.47
    query
    0.46
     Query
    0.46
    Renderer
    0.46
    Activations Density 0.006%

    No Known Activations