© 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. 32100
    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_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
    સ્પ
    0.16
     dissect
    0.16
    ೀರಿ
    0.16
     tissues
    0.15
     slides
    0.15
     stem
    0.14
    ド
    0.14
     estrat
    0.14
     fabricated
    0.14
    ᴘ
    0.14
    POSITIVE LOGITS
     gede
    0.16
    onnés
    0.16
     realizacji
    0.16
    嘴角
    0.16
     Wordsworth
    0.16
    aughton
    0.16
     ٹوٹ
    0.16
    胧
    0.16
    WBWB
    0.15
    愕
    0.15
    Activations Density 0.000%

    No Known Activations