© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142504
    Prev
    Next
    INDEX
    Explanations

    blood

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     작동
    0.39
     pét
    0.39
     consult
    0.38
     apar
    0.38
     牛
    0.38
     Servlet
    0.37
    riu
    0.37
     çek
    0.37
     DMF
    0.37
     flow
    0.37
    POSITIVE LOGITS
    onDidChange
    0.42
     glyphicon
    0.41
    陀
    0.41
    того
    0.41
     Crosby
    0.38
    Casa
    0.37
    hann
    0.37
    iazioni
    0.37
    fruit
    0.36
    curly
    0.36
    Activations Density 0.001%

    No Known Activations