© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198509
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_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
     দূ
    0.48
    𐰴
    0.48
     CharPtr
    0.48
     পাট
    0.47
     Ull
    0.45
    ن
    0.44
    KH
    0.44
    K
    0.44
     રાજ
    0.43
    лән
    0.43
    POSITIVE LOGITS
     death
    0.48
    ક્રિય
    0.48
     SERVICE
    0.45
     elbow
    0.43
     refuge
    0.43
     teeming
    0.42
     geometry
    0.42
     gate
    0.42
     esophagus
    0.41
     phishing
    0.41
    Activations Density 0.000%

    No Known Activations