© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172047
    Prev
    Next
    INDEX
    Explanations

    soft skills

    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_20_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
     条件
    0.27
    ṇa
    0.27
    收到
    0.26
     Nonprofit
    0.26
    σ
    0.25
    高
    0.25
    度
    0.25
     使用
    0.25
    确定
    0.25
     STYLE
    0.25
    POSITIVE LOGITS
    asthenia
    0.27
     prea
    0.24
    ayson
    0.24
     रहने
    0.24
    burden
    0.23
     পারে
    0.23
     Burden
    0.23
    rizioni
    0.23
    izons
    0.23
     приро
    0.22
    Activations Density 0.003%

    No Known Activations