© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87704
    Prev
    Next
    INDEX
    Explanations

    otaku Mode

    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_3_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
    在
    0.91
    ление
    0.78
    j
    0.77
    可以
    0.66
    jší
    0.65
    َ
    0.64
    B
    0.63
    し
    0.63
    ться
    0.61
    нок
    0.61
    POSITIVE LOGITS
    ด์
    0.84
    น่า
    0.69
     embold
    0.64
    s
    0.63
     as
    0.61
    alid
    0.61
    িলি
    0.60
    OutputFile
    0.60
    นิด
    0.60
     Chinatown
    0.59
    Activations Density 0.000%

    No Known Activations