© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206795
    Prev
    Next
    INDEX
    Explanations

    personal finance and life insurance

    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_37_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
     conserve
    0.44
     Tall
    0.38
     genü
    0.38
     کیس
    0.37
    nance
    0.36
    sprech
    0.36
     woning
    0.36
     conserver
    0.35
    캥
    0.35
    чого
    0.35
    POSITIVE LOGITS
    anyol
    0.38
     Spec
    0.37
    Spec
    0.37
    spec
    0.36
    }}+
    0.35
     Ferro
    0.34
    ','$
    0.34
    níku
    0.34
    alan
    0.33
    illard
    0.33
    Activations Density 0.001%

    No Known Activations