© 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
    2. Gemma-3-27B-IT
    3. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 4001
    Prev
    Next
    INDEX
    Explanations

    link rel

    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_39_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
    风格
    0.46
     Style
    0.44
     Stil
    0.44
     stil
    0.44
    কেমিক্যাল
    0.43
    䒷
    0.43
     पाउडर
    0.42
     сти
    0.41
     poudre
    0.41
     스타일
    0.41
    POSITIVE LOGITS
    draggable
    0.38
    Media
    0.38
    Г
    0.37
     matrícula
    0.37
    ╡
    0.37
     Г
    0.36
    insured
    0.36
    composer
    0.35
     வாழ்
    0.35
    Friends
    0.34
    Activations Density 0.004%

    No Known Activations