© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12166
    Prev
    Next
    INDEX
    Explanations

    stand mixer

    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
    </h1>
    0.39
    Func
    0.39
     resides
    0.37
     permanente
    0.37
    हल
    0.36
    महल
    0.35
     synapse
    0.35
    fte
    0.35
    alc
    0.35
    Forum
    0.35
    POSITIVE LOGITS
    กับ
    0.47
     सोबत
    0.43
    쮿
    0.43
     μέσω
    0.42
     लालू
    0.40
    ☦
    0.39
     ส่วน
    0.38
    <0x91>
    0.38
     hätte
    0.38
    лі
    0.37
    Activations Density 0.065%

    No Known Activations