© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 184006
    Prev
    Next
    INDEX
    Explanations

    Daily Express headlines

    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_29_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
     drugs
    0.45
     aided
    0.45
     insulated
    0.40
    氹
    0.40
     Drugs
    0.39
     assisted
    0.38
     church
    0.38
     insulation
    0.37
     libraries
    0.37
    drugs
    0.37
    POSITIVE LOGITS
    綪
    0.38
    振り返
    0.38
    мар
    0.36
    νοντας
    0.36
    fäh
    0.35
    ませんが
    0.35
    아버지
    0.35
    యన్స్
    0.35
    繹
    0.34
    昨日
    0.34
    Activations Density 0.001%

    No Known Activations