© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259830
    Prev
    Next
    INDEX
    Explanations

    if not handled carefully

    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_22_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
     persistent
    0.22
    🇪
    0.22
     steam
    0.22
    Engel
    0.22
     Crowley
    0.22
     favourite
    0.21
     Zhu
    0.21
     Raúl
    0.21
    🇨
    0.21
     ஹெ
    0.21
    POSITIVE LOGITS
     auquel
    0.29
    னுடன்
    0.28
    alne
    0.28
     émissions
    0.28
    をご確認
    0.28
     робити
    0.27
    getWriter
    0.27
    apons
    0.26
     houve
    0.26
    ড়ের
    0.26
    Activations Density 0.001%

    No Known Activations