© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 37009
    Prev
    Next
    INDEX
    Explanations

    company names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    autes
    0.42
     Blades
    0.42
     blades
    0.40
    ment
    0.39
    asts
    0.39
    titles
    0.37
    ]{\
    0.37
     Needs
    0.37
     столб
    0.36
     pipes
    0.36
    POSITIVE LOGITS
    CNN
    0.42
     disgraceful
    0.41
    푥
    0.40
     mercados
    0.40
     ваго
    0.40
    يفي
    0.39
     कॉमन
    0.38
     CNN
    0.37
    マイクロ
    0.37
    ZN
    0.37
    Activations Density 0.007%

    No Known Activations