© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237188
    Prev
    Next
    INDEX
    Explanations

    markdown headings from 2 to 6

    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_25_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
     Erect
    0.27
     અન
    0.26
     unnatural
    0.26
     Glendale
    0.25
     gunman
    0.25
    惱
    0.25
     December
    0.25
     Apollo
    0.25
    ্মদ
    0.24
    額
    0.24
    POSITIVE LOGITS
    lets
    0.26
    ทั้ง
    0.25
    transparent
    0.24
     managed
    0.24
    rencies
    0.24
    透明
    0.23
    龙头
    0.23
    pmatrix
    0.23
     żeby
    0.23
     прозра
    0.23
    Activations Density 0.002%

    No Known Activations