© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24773
    Prev
    Next
    INDEX
    Explanations

    numbers and quantitative data

    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_56_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
    BRAND
    0.37
    नाने
    0.36
     embassy
    0.34
     superst
    0.34
     celebrity
    0.34
     celeb
    0.34
    রাগ
    0.34
    堂
    0.33
    πων
    0.33
    精
    0.32
    POSITIVE LOGITS
    ivali
    0.39
    ပြ
    0.36
    amazaki
    0.36
    vira
    0.36
     tro
    0.36
     تاثیر
    0.35
    uhan
    0.35
     afet
    0.35
     discern
    0.34
     बेहत
    0.34
    Activations Density 0.066%

    No Known Activations