© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223171
    Prev
    Next
    INDEX
    Explanations

    olive oil, olive skin, olive branches

    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_10_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
    ts
    0.24
    the
    0.22
     a
    0.22
    akes
    0.21
    ल
    0.21
    aws
    0.21
    ma
    0.20
    MA
    0.20
    Т
    0.20
    Ch
    0.20
    POSITIVE LOGITS
     Kaise
    0.21
     Lite
    0.20
     RSC
    0.20
     HBase
    0.20
    एसआय
    0.19
     handyman
    0.19
     Symbols
    0.19
     THIRD
    0.19
     Ribbon
    0.19
     Seite
    0.19
    Activations Density 0.003%

    No Known Activations