© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84383
    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_23_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
     Jarvis
    0.42
     outstanding
    0.41
    მ
    0.41
     Inform
    0.41
     encompasses
    0.40
    elementProp
    0.39
     Jamestown
    0.39
     Sess
    0.38
    윽
    0.38
    Grim
    0.38
    POSITIVE LOGITS
     théorème
    0.52
     pracę
    0.51
    Databaze
    0.50
     posticis
    0.49
     aktor
    0.48
     spaceShip
    0.48
     nonché
    0.48
     necessário
    0.47
     clickView
    0.46
    âteaux
    0.46
    Activations Density 0.000%

    No Known Activations