© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172256
    Prev
    Next
    INDEX
    Explanations

    I asked, I would, I need, How can

    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_20_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
     sculpture
    0.15
     byrow
    0.14
    钤
    0.14
     липня
    0.13
     berapa
    0.13
     octobre
    0.13
     atrib
    0.13
    년간
    0.13
    ági
    0.13
    uro
    0.13
    POSITIVE LOGITS
     likewise
    0.15
     Likewise
    0.15
    上下文
    0.14
    Synced
    0.14
     كذلك
    0.14
     “[
    0.14
    Likewise
    0.13
     Nineteenth
    0.13
     hydride
    0.13
    Folders
    0.13
    Activations Density 0.003%

    No Known Activations