© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175630
    Prev
    Next
    INDEX
    Explanations

    ```commands following slashes```

    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_24_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
     ಮುಂದೆ
    0.31
    籮
    0.30
    ối
    0.30
    ților
    0.29
    τρα
    0.29
    頑
    0.29
     Draper
    0.28
     비롯
    0.28
     Garage
    0.28
    marie
    0.28
    POSITIVE LOGITS
    锢
    0.30
    法则
    0.30
    বহ
    0.30
    了吧
    0.29
     isolated
    0.29
    Телефон
    0.29
    客户
    0.28
    UserModel
    0.28
     ins
    0.28
     cirk
    0.27
    Activations Density 0.001%

    No Known Activations