© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    4. 79927
    Prev
    Next
    INDEX
    Explanations

    you

    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_53_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
    乌
    0.42
    setRoi
    0.40
    ꩡ
    0.38
    PackageReference
    0.36
    烏
    0.36
     calming
    0.35
    ISM
    0.35
    研发
    0.34
     MeV
    0.34
    新建
    0.33
    POSITIVE LOGITS
     Mér
    0.45
     b
    0.42
    mer
    0.41
    ekyll
    0.40
    housing
    0.39
     billy
    0.39
     freak
    0.38
    мере
    0.38
     cactus
    0.38
     pong
    0.38
    Activations Density 0.003%

    No Known Activations