© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40085
    Prev
    Next
    INDEX
    Explanations

    money order or monotherapy

    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_3_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
    ються
    0.64
    המ
    0.63
    มนเชสเตอร์
    0.62
     사이에
    0.62
    ╫
    0.62
    その
    0.60
    nilvadipine
    0.60
     allotments
    0.59
    ワゴン
    0.59
    ו
    0.58
    POSITIVE LOGITS
    F
    0.92
    ),
    0.88
    ة
    0.87
    ing
    0.80
    ES
    0.79
    те
    0.75
    ET
    0.72
    );
    0.71
    ,"
    0.70
     be
    0.67
    Activations Density 0.004%

    No Known Activations