© 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. 166283
    Prev
    Next
    INDEX
    Explanations

    little + [name/noun]

    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
     rarely
    0.44
    nonatomic
    0.41
     только
    0.41
     hardly
    0.41
     一个
    0.40
     আর
    0.39
     רק
    0.38
    柩
    0.38
     Rarely
    0.37
     Sadly
    0.37
    POSITIVE LOGITS
     creases
    0.43
    เฟ
    0.40
     sausages
    0.40
     ہوجائیں
    0.40
     vertices
    0.38
     sc
    0.37
    菲
    0.37
    ="/"
    0.37
     spiders
    0.35
     cip
    0.35
    Activations Density 0.001%

    No Known Activations