© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167049
    Prev
    Next
    INDEX
    Explanations

    materials and equipment

    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_31_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
    较大
    0.44
    较高
    0.42
    较
    0.38
     excelled
    0.38
    較
    0.37
     email
    0.37
    较大的
    0.36
    追
    0.36
    受
    0.35
    orderby
    0.35
    POSITIVE LOGITS
    看不到
    0.41
    ครื่อง
    0.41
     pomeriggio
    0.38
     poured
    0.38
    PipelineState
    0.38
     Spirit
    0.37
     বিকাল
    0.37
     pouring
    0.37
    Crew
    0.37
     രാവിലെ
    0.36
    Activations Density 0.001%

    No Known Activations