© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 43795
    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_13_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
    Deutsch
    0.51
     aise
    0.50
    функ
    0.50
    戽
    0.50
     Jeu
    0.49
    Sorry
    0.49
    껍
    0.48
     soggy
    0.48
     речи
    0.48
     الدولي
    0.48
    POSITIVE LOGITS
     concatenate
    0.57
    2
    0.55
    ism
    0.55
    ванням
    0.53
    codename
    0.53
    agana
    0.53
     limit
    0.52
    ên
    0.52
    )]
    0.50
     Seafood
    0.49
    Activations Density 0.000%

    No Known Activations