© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198298
    Prev
    Next
    INDEX
    Explanations

    building

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Had
    0.39
    Ｗ
    0.39
    вець
    0.39
    phine
    0.39
    Absolutely
    0.38
    泾
    0.38
    mice
    0.38
    Wat
    0.37
    Wh
    0.37
    férences
    0.36
    POSITIVE LOGITS
     역
    0.37
    শ্ত
    0.36
     poser
    0.36
     pretext
    0.35
    磚
    0.35
    リュ
    0.35
     largest
    0.35
    Largest
    0.35
    htm
    0.34
     Mini
    0.34
    Activations Density 0.001%

    No Known Activations