© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76655
    Prev
    Next
    INDEX
    Explanations

    vector components or lists

    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_31_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
     杨
    0.41
    Garcia
    0.37
    èves
    0.36
    weig
    0.34
     Salvatore
    0.33
     Asimismo
    0.33
     veniam
    0.32
     Garcia
    0.31
    Ɔ
    0.31
     dajj
    0.31
    POSITIVE LOGITS
     bagian
    0.38
     causation
    0.38
     delineation
    0.37
     Sargent
    0.37
     தெளி
    0.36
     применя
    0.35
    ubarb
    0.34
     жер
    0.34
     Constituency
    0.33
     пери
    0.33
    Activations Density 0.002%

    No Known Activations