© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17921
    Prev
    Next
    INDEX
    Explanations

    filters and filtration

    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_34_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
     Reflect
    0.38
    一件
    0.36
    Landing
    0.36
    ╴
    0.36
     Scar
    0.36
    Scar
    0.36
    landing
    0.35
     Zoom
    0.35
    Zoom
    0.35
    镐
    0.35
    POSITIVE LOGITS
     filters
    1.06
     filter
    0.95
     filtre
    0.95
    filters
    0.94
     Filters
    0.93
     filtros
    0.93
     filtro
    0.93
    过滤器
    0.91
     filtration
    0.90
     филь
    0.89
    Activations Density 0.078%

    No Known Activations