© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 87074
    Prev
    Next
    INDEX
    Explanations

    code instantiation

    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_23_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
     素材
    0.44
    素材
    0.43
    甪
    0.43
    幔
    0.38
     टेस्ट
    0.38
    material
    0.37
    镁
    0.37
    测试
    0.37
    ards
    0.37
     विवाद
    0.37
    POSITIVE LOGITS
     contributed
    0.38
     kdo
    0.38
     independent
    0.37
    ęd
    0.37
     independiente
    0.37
     marked
    0.36
    NETT
    0.36
     outstanding
    0.36
     served
    0.36
     tagged
    0.35
    Activations Density 0.001%

    No Known Activations