© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35922
    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_50_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
    ành
    0.44
    onz
    0.41
    庥
    0.39
    オン
    0.38
     ৫ম
    0.38
    ించడానికి
    0.38
     interesa
    0.37
    மொழி
    0.37
     finisher
    0.37
    冖
    0.37
    POSITIVE LOGITS
    сій
    0.41
    semibold
    0.41
     ಮಿಶ್ರ
    0.39
     аку
    0.39
     aureus
    0.39
    aust
    0.38
     atom
    0.37
     frecu
    0.37
     Tompkins
    0.37
    වා
    0.37
    Activations Density 0.000%

    No Known Activations