© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78555
    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_53_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
     mo
    0.45
     explos
    0.40
    mygray
    0.40
    ວນ
    0.39
    砣
    0.39
     haz
    0.39
    詭
    0.39
    ವರಿ
    0.38
    ರಲ್ಲಿ
    0.38
     Bryant
    0.37
    POSITIVE LOGITS
    ucch
    0.42
    b
    0.41
    try
    0.39
    SSE
    0.36
    tre
    0.36
     botas
    0.35
     sélectionnez
    0.35
     materias
    0.35
    บท
    0.34
     поку
    0.34
    Activations Density 0.000%

    No Known Activations