© 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. 218748
    Prev
    Next
    INDEX
    Explanations

    Adjust CSS/HTML properties

    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
     உப்பு
    0.42
    cheduler
    0.40
     ISLAND
    0.39
    WebpackPlugin
    0.39
    edTest
    0.38
    묶
    0.38
     muri
    0.38
     SAL
    0.38
     группу
    0.38
    ":{"
    0.37
    POSITIVE LOGITS
     DVD
    0.37
     улице
    0.37
     مقدار
    0.36
    android
    0.35
    androidx
    0.35
     elucidate
    0.35
    ariah
    0.35
     Oatmeal
    0.35
     کس
    0.35
     Dirac
    0.35
    Activations Density 0.005%

    No Known Activations