© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53964
    Prev
    Next
    INDEX
    Explanations

    you are

    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_30_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
    육
    0.40
     ارتفاع
    0.39
     육
    0.38
     آنچه
    0.37
     TFS
    0.37
    的意思
    0.37
    oprene
    0.37
    咅
    0.37
     Володи
    0.37
     입니다
    0.36
    POSITIVE LOGITS
     särsk
    0.44
     sør
    0.38
     sikre
    0.38
     blushing
    0.37
    𝟎
    0.37
    soo
    0.37
    dehyde
    0.36
    so
    0.36
     sûr
    0.35
    emo
    0.35
    Activations Density 0.016%

    No Known Activations