© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240284
    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
     Comprehensive
    0.46
     Formation
    0.44
     And
    0.41
     تاہم
    0.41
     откуда
    0.41
     Honour
    0.40
    management
    0.40
    赵
    0.40
    区别
    0.40
     Applied
    0.39
    POSITIVE LOGITS
    REY
    0.42
    릴
    0.41
    тли
    0.39
     сосед
    0.39
    פתח
    0.39
     gosto
    0.38
    рэ
    0.38
    рино
    0.38
    爪
    0.38
    Fif
    0.37
    Activations Density 0.000%

    No Known Activations