© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    4. 81891
    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
    允许
    0.48
     தோ
    0.48
     亻
    0.48
    谋
    0.46
     mejorar
    0.46
    用の
    0.46
     操作
    0.45
     万元
    0.45
     የሚ
    0.45
     زمین
    0.45
    POSITIVE LOGITS
    ,
    0.60
    ,...
    0.55
     dritte
    0.53
     Bols
    0.52
    ...)
    0.51
     (...)
    0.50
    Coca
    0.49
     Compagnie
    0.49
    ]
    0.49
    ...,
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.