© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 198035
    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
    Creator
    0.40
    फिकेशन
    0.39
    呎
    0.38
    ज़्
    0.38
    Mi
    0.38
    fas
    0.37
    jár
    0.36
     olen
    0.36
    jats
    0.36
     T
    0.36
    POSITIVE LOGITS
     ელ
    0.38
    央
    0.38
     RIN
    0.37
     intran
    0.37
    textepsilon
    0.36
    キャ
    0.36
    クール
    0.36
     Caball
    0.36
     senior
    0.35
     cabel
    0.35
    Activations Density 0.000%

    No Known Activations