© 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. 139392
    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
     устра
    0.44
    Em
    0.39
    SCRIPT
    0.39
    ToSend
    0.39
     Em
    0.38
    ायचे
    0.38
     Facilities
    0.38
    庶
    0.37
    ลักษณ์
    0.37
    报道
    0.36
    POSITIVE LOGITS
     gli
    0.51
     Gli
    0.42
     dagli
    0.40
     midwifery
    0.38
    Gli
    0.38
     prophes
    0.38
     absorbs
    0.37
     maç
    0.37
     prophecy
    0.36
     maggiore
    0.36
    Activations Density 0.000%

    No Known Activations