© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13172
    Prev
    Next
    INDEX
    Explanations

    exclude or exempt

    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_13_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
    with
    0.33
    라운
    0.33
     нём
    0.31
    بوع
    0.31
     പ്രവർത്തന
    0.31
    ルーム
    0.31
    は
    0.30
    from
    0.30
    you
    0.30
    6
    0.30
    POSITIVE LOGITS
    
    0.38
     झाल्यावर
    0.33
     paes
    0.32
     mortem
    0.31
    ﺹ
    0.31
     sear
    0.29
     scelto
    0.29
    ক্ষেত্র
    0.29
     pressed
    0.29
    ḓ
    0.29
    Activations Density 0.151%

    No Known Activations