© 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
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159523
    Prev
    Next
    INDEX
    Explanations

    skimage and sklearn imports

    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_2_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
    IS
    1.10
    <h2>
    1.01
    С
    0.96
    সহিত
    0.96
     tři
    0.94
    М
    0.94
    اني
    0.91
     všech
    0.91
     نہيں
    0.91
    CODES
    0.88
    POSITIVE LOGITS
    로
    1.52
    లు
    1.36
     in
    1.35
    ra
    1.31
    ור
    1.31
    ون
    1.29
    نا
    1.29
    ها
    1.28
    ก
    1.28
    ある
    1.26
    Activations Density 0.000%

    No Known Activations