© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210634
    Prev
    Next
    INDEX
    Explanations

    focal point

    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_20_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
    水量
    0.51
     वॉटर
    0.46
     நீர்
    0.42
     مقدار
    0.41
    του
    0.40
    潙
    0.39
     WEATHER
    0.38
     जल
    0.38
    它们
    0.38
     πι
    0.38
    POSITIVE LOGITS
     importance
    0.47
    /}{
    0.44
     prides
    0.44
    ˈ
    0.44
     casco
    0.43
     multiplets
    0.41
     collaborations
    0.41
    pencil
    0.41
    劍
    0.41
     должен
    0.40
    Activations Density 0.001%

    No Known Activations