© 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. 172124
    Prev
    Next
    INDEX
    Explanations

    Windows operating system features

    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
     आजही
    0.35
     Catar
    0.34
    ግብ
    0.34
    仍然
    0.33
    ᱖
    0.33
     serendip
    0.32
     dgn
    0.32
     সেজন্য
    0.32
    ﭥ
    0.32
    هن
    0.32
    POSITIVE LOGITS
    strukt
    0.33
    Permissions
    0.31
    чення
    0.31
    structures
    0.31
    ostructures
    0.31
     метода
    0.31
    ustes
    0.31
    су
    0.30
    ке
    0.30
     hefty
    0.30
    Activations Density 0.008%

    No Known Activations