© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36514
    Prev
    Next
    INDEX
    Explanations

    EA code snippets

    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
    Ⴀ
    0.44
    ensky
    0.42
    arness
    0.41
     березня
    0.40
    亞洲
    0.40
    casian
    0.39
     Smithsonian
    0.38
    ่านั้น
    0.38
    hexahydro
    0.38
    例如
    0.38
    POSITIVE LOGITS
     recl
    0.40
     lines
    0.39
     líneas
    0.39
     traces
    0.38
     ತ
    0.38
     Gren
    0.37
    Watts
    0.37
    Claude
    0.37
     seals
    0.36
     Watts
    0.36
    Activations Density 0.000%

    No Known Activations