© 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. 55191
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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
     led
    0.41
     liar
    0.39
     BIP
    0.38
     todo
    0.38
     silent
    0.38
     quantities
    0.38
     […]
    0.38
     mue
    0.37
    لينكات
    0.37
     wonderful
    0.37
    POSITIVE LOGITS
     मल्टीप्लिकेशन
    0.46
    3
    0.45
     algéb
    0.44
    Subtraction
    0.41
    Addition
    0.41
    6
    0.41
    级
    0.40
    чис
    0.40
    Subtract
    0.40
     मल्टीप्लाई
    0.40
    Activations Density 0.008%

    No Known Activations