© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 81222
    Prev
    Next
    INDEX
    Explanations

    foreign language prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_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
    ]]).
    0.45
    的話
    0.42
    ğiniz
    0.39
     actionBar
    0.39
     Gres
    0.39
    ൩
    0.39
    荠
    0.38
    雔
    0.38
    ﺕ
    0.38
     który
    0.38
    POSITIVE LOGITS
     zone
    0.37
    channel
    0.37
     channel
    0.37
     suya
    0.37
    mailing
    0.36
     swab
    0.35
     drives
    0.35
    est
    0.35
    auce
    0.35
     suppose
    0.34
    Activations Density 0.005%

    No Known Activations