© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141803
    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_0_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
    ي
    1.55
    ون
    1.52
    i
    1.44
    ut
    1.43
    ak
    1.38
    á
    1.30
     a
    1.25
    아
    1.24
    ਾ
    1.23
    ‌ها
    1.23
    POSITIVE LOGITS
    .
    1.90
    ного
    1.50
    cient
    1.43
    зыва
    1.29
     kurulu
    1.28
    cence
    1.27
    ное
    1.27
     cerve
    1.26
     cherish
    1.26
     brighten
    1.26
    Activations Density 0.000%

    No Known Activations