© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107719
    Prev
    Next
    INDEX
    Explanations

    reign or sovereign

    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_1_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
    et
    1.42
    ى
    1.30
    an
    1.20
    ны
    1.20
    a
    1.20
    м
    1.16
    า
    1.16
    т
    1.13
    at
    1.10
    <0x80>
    1.09
    POSITIVE LOGITS
    ão
    1.16
    (
    1.16
    ))
    1.07
     hypothes
    1.05
    ,
    1.05
     riots
    1.04
     tessuto
    1.02
    に
    1.02
    ){
    1.00
    เป็น
    1.00
    Activations Density 0.001%

    No Known Activations