© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206346
    Prev
    Next
    INDEX
    Explanations

    financial crisis

    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_19_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     superfluous
    0.28
    鏨
    0.27
     hallmarks
    0.26
    𝟖
    0.26
     kobiet
    0.25
     Ghaz
    0.25
     salarié
    0.25
    </b>
    0.25
    lookup
    0.25
    利益
    0.25
    POSITIVE LOGITS
     if
    0.29
    श्च
    0.29
     nếu
    0.25
    到
    0.25
     installs
    0.25
     않으면
    0.25
     कसे
    0.24
    _{
    0.24
     Nếu
    0.24
     muốn
    0.24
    Activations Density 0.004%

    No Known Activations