© 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
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167817
    Prev
    Next
    INDEX
    Explanations

    levels or layers

    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_56_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
    的故事
    0.38
    unii
    0.38
    äts
    0.37
    éticas
    0.36
    ާއ
    0.36
    getQuery
    0.36
    前面的
    0.35
    ㅢ
    0.35
    鉉
    0.35
    这样的
    0.35
    POSITIVE LOGITS
     hàng
    1.10
    ชั้น
    0.75
    继
    0.68
     ชั้น
    0.67
    仅
    0.64
     terl
    0.59
    僅
    0.55
     tert
    0.50
    繼
    0.48
     strata
    0.46
    Activations Density 0.003%

    No Known Activations