© 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. 203857
    Prev
    Next
    INDEX
    Explanations

    electrical and magnetic

    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
     useParams
    0.38
    Ἐ
    0.38
     прос
    0.36
    En
    0.35
    ric
    0.35
    xE
    0.35
    spreadsheet
    0.34
    surprise
    0.34
    គេ
    0.33
     εν
    0.32
    POSITIVE LOGITS
    磁
    0.40
     magnétique
    0.40
    चित
    0.39
    ówka
    0.39
    gång
    0.38
    emaster
    0.38
    িকা
    0.38
     দুর্নীতি
    0.38
    েনার
    0.38
    पंथी
    0.37
    Activations Density 0.000%

    No Known Activations