© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6570
    Prev
    Next
    INDEX
    Explanations

    Gaussian additive noise

    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_44_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
    вери
    0.39
    icosa
    0.39
    плення
    0.37
     Duncan
    0.36
    ierrez
    0.36
     বক্স
    0.36
    itakan
    0.36
    蒡
    0.36
    बली
    0.35
     फ्लू
    0.35
    POSITIVE LOGITS
     Gaussian
    0.54
    Gaussian
    0.52
    Additive
    0.46
    additive
    0.46
     additive
    0.46
     AW
    0.45
     Gauss
    0.43
     CFO
    0.42
    determin
    0.42
    CW
    0.42
    Activations Density 0.114%

    No Known Activations