© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48590
    Prev
    Next
    INDEX
    Explanations

    say "and"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     এবং
    0.46
     OR
    0.46
     AND
    0.45
     và
    0.44
     &
    0.43
     आणि
    0.42
     thiab
    0.42
    并且
    0.42
     மற்றும்
    0.41
     և
    0.41
    POSITIVE LOGITS
     uniqu
    0.38
     accesible
    0.37
     sharedInstance
    0.36
     getDateTime
    0.36
     மையம்
    0.34
    隐含规则
    0.34
    buttonLevel
    0.34
    恳
    0.34
    ளமான
    0.33
     converts
    0.33
    Activations Density 0.028%

    No Known Activations