© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35646
    Prev
    Next
    INDEX
    Explanations

    like Google, OpenCV, film, chat

    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_7_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
     eyebrows
    0.31
     aptly
    0.30
     it
    0.29
     GFP
    0.29
     Figure
    0.29
     NPP
    0.28
     no
    0.28
     Ν
    0.28
     NOx
    0.28
    ↵
    0.27
    POSITIVE LOGITS
    지
    0.31
    <0x80>
    0.26
    اب
    0.25
    ى
    0.24
    ва
    0.23
    في
    0.23
    (
    0.22
    ве
    0.22
    شي
    0.21
    ,
    0.21
    Activations Density 0.018%

    No Known Activations