© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83026
    Prev
    Next
    INDEX
    Explanations

    python code syntax

    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
     дві
    0.37
    ơi
    0.37
    şık
    0.37
    voř
    0.36
    ônica
    0.34
    윳
    0.33
    HIV
    0.33
    劵
    0.33
     রক্তাক্ত
    0.33
    zī
    0.33
    POSITIVE LOGITS
    արգ
    0.41
     широ
    0.37
     wider
    0.36
    ላለ
    0.36
    च्छ
    0.36
     declinations
    0.33
     both
    0.33
     Oe
    0.33
     zár
    0.32
     Basil
    0.32
    Activations Density 0.012%

    No Known Activations