© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17865
    Prev
    Next
    INDEX
    Explanations

    URL and password references

    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_40_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
     ର
    0.30
    ToAction
    0.30
     використання
    0.30
    Inher
    0.30
     hérit
    0.30
     dispose
    0.29
     такого
    0.28
     Clín
    0.28
     ಅಲ
    0.28
    /}
    0.28
    POSITIVE LOGITS
     ferry
    0.33
     hoon
    0.29
     shelved
    0.28
    嵩
    0.28
     Durch
    0.28
     ferries
    0.28
     gennem
    0.28
    不能为空
    0.27
    spiracy
    0.27
     scratches
    0.27
    Activations Density 0.000%

    No Known Activations