© 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. 48741
    Prev
    Next
    INDEX
    Explanations

    subtraction multiplication

    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
    Not in Any Lists

    No Comments

    Negative Logits
    oxing
    0.40
    ேக
    0.37
     갖고
    0.37
     }()
    0.35
     छू
    0.35
     *}(
    0.35
     '{}
    0.34
     بڑ
    0.34
    ="("
    0.33
     ofstream
    0.33
    POSITIVE LOGITS
     subtract
    0.49
     subtraction
    0.46
     subtracted
    0.46
     subtracting
    0.44
    subtract
    0.40
     Tribute
    0.39
     Mul
    0.38
     Cruise
    0.38
    乘以
    0.38
    Subtraction
    0.38
    Activations Density 0.001%

    No Known Activations