© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41152
    Prev
    Next
    INDEX
    Explanations

    uranium, plutonium, radioactive waste, nuclear fuel

    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_11_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
    ate
    0.41
    BE
    0.41
    OR
    0.39
    ely
    0.39
    álni
    0.39
    ables
    0.39
    aka
    0.39
    ally
    0.38
    they
    0.38
    '
    0.38
    POSITIVE LOGITS
    ై
    0.47
    庥
    0.46
     hoofdst
    0.43
    शेदपुर
    0.43
     indole
    0.43
    强化
    0.42
     ribonucle
    0.42
    రి
    0.41
    ವಿ
    0.41
    ರುತ್ತದೆ
    0.41
    Activations Density 0.037%

    No Known Activations