© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31832
    Prev
    Next
    INDEX
    Explanations

    phrase or category

    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_31_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
    }}]{
    0.39
     ketika
    0.39
     Ketika
    0.38
     when
    0.37
     Johansson
    0.34
    尕
    0.34
     когда
    0.34
    }^{(\
    0.34
     ತಿಳಿದ
    0.34
     رکن
    0.34
    POSITIVE LOGITS
     உள்ளட
    0.42
     class
    0.38
    class
    0.38
    ordes
    0.37
    вили
    0.37
    ប្រភេទ
    0.37
    рая
    0.37
    压力
    0.36
    銷售
    0.36
     DER
    0.36
    Activations Density 0.065%

    No Known Activations