© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204563
    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_25_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
    ená
    0.41
    સ્
    0.40
     çeşitli
    0.40
    ća
    0.39
     grupp
    0.39
    歿
    0.38
     která
    0.38
     konuş
    0.37
     fêtes
    0.36
     partenariat
    0.36
    POSITIVE LOGITS
    ace
    0.36
    と同
    0.35
     MC
    0.35
    ouncer
    0.34
    วัง
    0.34
    かに
    0.34
    럭
    0.34
    ώ
    0.34
     pani
    0.33
     চিত্ত
    0.33
    Activations Density 0.000%

    No Known Activations