© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122343
    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_37_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
     パーカー
    0.39
    Lips
    0.37
     ませ
    0.36
     밀
    0.36
     mantle
    0.36
     elections
    0.35
     Exploration
    0.35
     vind
    0.35
    䫝
    0.35
     Authorization
    0.35
    POSITIVE LOGITS
    Len
    0.42
    வையும்
    0.37
    োন
    0.36
    tear
    0.35
    NAL
    0.35
    Tunes
    0.35
    撕
    0.34
    bin
    0.34
    Pup
    0.34
    khar
    0.34
    Activations Density 0.000%

    No Known Activations