© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199794
    Prev
    Next
    INDEX
    Explanations

    game loop break

    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_27_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
    ]]]]
    0.42
    的原因
    0.41
    ]\
    0.40
    后的
    0.40
    数字
    0.39
    ющимся
    0.39
    戈
    0.37
     digitization
    0.37
    ])){
    0.37
    VIEWS
    0.36
    POSITIVE LOGITS
    霈
    0.38
    nic
    0.38
     Emit
    0.38
    nicy
    0.37
     vibe
    0.36
    theta
    0.36
     worship
    0.36
     afore
    0.36
     podczas
    0.36
    ników
    0.36
    Activations Density 0.001%

    No Known Activations