© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5054
    Prev
    Next
    INDEX
    Explanations

    units with division or physical quantities

    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
    移
    0.35
     DEPEND
    0.34
    ᓛ
    0.34
    unload
    0.33
    asida
    0.32
    Penny
    0.32
     Penny
    0.32
     निर्देशक
    0.31
    garakan
    0.30
     Publisher
    0.30
    POSITIVE LOGITS
     per
    0.66
    per
    0.47
     لكل
    0.41
     Per
    0.35
     :=
    0.34
     kg
    0.33
    illegal
    0.33
    liter
    0.33
     fonte
    0.32
     kilowatt
    0.32
    Activations Density 0.035%

    No Known Activations