© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90443
    Prev
    Next
    INDEX
    Explanations

    space exploration

    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_11_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
     ресто
    0.64
    ຣ
    0.58
    v
    0.57
    kapet
    0.53
    Ј
    0.53
    రించ
    0.52
     цін
    0.52
     จ
    0.50
    身后
    0.50
     бесе
    0.50
    POSITIVE LOGITS
    щая
    0.62
     dehydration
    0.52
    될
    0.52
     creation
    0.50
     Spoiler
    0.50
     SSI
    0.48
    ──
    0.48
     Metadata
    0.47
     serialization
    0.47
    化粧
    0.47
    Activations Density 0.021%

    No Known Activations