© 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. 220092
    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
    🕉
    0.38
     thôn
    0.37
    alley
    0.36
    ЕЛЬ
    0.36
    噸
    0.36
     sturdy
    0.35
    ண்ணாம
    0.35
    ৳
    0.34
    |$
    0.34
     صندوق
    0.34
    POSITIVE LOGITS
     Europeans
    0.43
     daytime
    0.40
     folate
    0.40
     electrons
    0.37
     Fol
    0.37
     Europe
    0.36
     Phoebe
    0.36
     Iber
    0.36
     ak
    0.36
     Ak
    0.36
    Activations Density 0.000%

    No Known Activations