© 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. 7616
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
     parameters
    0.18
     n
    0.17
    SMA
    0.17
    ikal
    0.17
     Parameters
    0.16
    num
    0.16
    ilda
    0.16
     num
    0.16
     castings
    0.16
    ifice
    0.16
    POSITIVE LOGITS
     ভিত্ত
    0.18
     Diffraction
    0.18
    圯
    0.17
     эко
    0.17
    뜯
    0.17
     بھ
    0.17
    sparsebundle
    0.17
     งาน
    0.17
     Pid
    0.17
     Uno
    0.16
    Activations Density 0.004%

    No Known Activations