© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207129
    Prev
    Next
    INDEX
    Explanations

    foreign or non-english words

    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_19_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
    và
    0.16
     మరియు
    0.16
    ѳ
    0.15
     Watan
    0.15
    డాది
    0.15
     Halke
    0.14
     성능
    0.14
     isEqual
    0.14
    кинуло
    0.14
     ਅਤੇ
    0.14
    POSITIVE LOGITS
     toute
    0.14
    ไม
    0.14
    越
    0.14
     !)
    0.14
    brecht
    0.14
     excess
    0.13
     façon
    0.13
    温柔
    0.13
     fondamental
    0.13
     കാല
    0.13
    Activations Density 0.046%

    No Known Activations