© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166739
    Prev
    Next
    INDEX
    Explanations

    html head tag

    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_31_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
     miras
    0.40
    ྵ
    0.38
    uruh
    0.38
    वैसे
    0.38
     করলো
    0.38
    CharPtr
    0.38
     resto
    0.37
    မှာ
    0.37
    :“
    0.37
    UTO
    0.36
    POSITIVE LOGITS
     сорта
    0.36
     cuant
    0.34
     ቀ
    0.33
     السود
    0.33
     Morning
    0.33
     Tsing
    0.33
     numb
    0.33
    Mathemat
    0.33
     मियां
    0.33
     неде
    0.32
    Activations Density 0.001%

    No Known Activations