© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    4. 3805
    Prev
    Next
    INDEX
    Explanations

    finance and costs

    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_44_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
    加拿大
    0.40
    Youth
    0.40
     youth
    0.39
    蚪
    0.38
    佞
    0.37
    IRST
    0.37
    らが
    0.37
     الصحي
    0.34
    秅
    0.34
    专题
    0.34
    POSITIVE LOGITS
     Sq
    0.46
     Stretching
    0.39
     ubr
    0.39
    numbered
    0.37
    Hamburg
    0.37
    Stretch
    0.37
     numbered
    0.37
     Blocking
    0.36
    ሢ
    0.36
     Hamburg
    0.36
    Activations Density 0.001%

    No Known Activations