© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13880
    Prev
    Next
    INDEX
    Explanations

    host/server assignment

    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_15_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
    ייתה
    0.33
    }}{\
    0.31
    사용
    0.31
     vấn
    0.31
    홧
    0.30
    ட்டத்தில்
    0.30
     използ
    0.30
     reagents
    0.30
     statuses
    0.29
    တ
    0.29
    POSITIVE LOGITS
     supermarkets
    0.38
     lä
    0.37
     स्थानांतरित
    0.37
     Senate
    0.36
     senate
    0.36
    would
    0.34
     Auch
    0.34
     bookstores
    0.34
     Income
    0.33
     would
    0.32
    Activations Density 0.024%

    No Known Activations