© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1376
    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_39_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
    Dutch
    0.47
     Dutch
    0.44
     Belanda
    0.42
     Dutchman
    0.40
     +#
    0.39
    ierende
    0.39
    French
    0.38
     dutch
    0.38
    Rivers
    0.38
     प्रीमियम
    0.38
    POSITIVE LOGITS
     Corso
    0.41
    キスト
    0.40
    覽
    0.40
     San
    0.38
     Scop
    0.38
     tasso
    0.37
     הת
    0.37
    tra
    0.36
    ულ
    0.36
    Cô
    0.36
    Activations Density 0.030%

    No Known Activations