© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7484
    Prev
    Next
    INDEX
    Explanations

    prepended qualifiers

    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_39_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
     palk
    0.44
     forbid
    0.41
     proporción
    0.37
    guardo
    0.37
     forbids
    0.36
     τραγ
    0.36
     forbade
    0.36
    圓
    0.35
    writeValue
    0.34
    pagina
    0.33
    POSITIVE LOGITS
     modifiers
    1.18
     modifier
    1.16
     qualifier
    1.09
     Modifier
    1.05
    Modifier
    1.05
     qualifiers
    1.03
    modifiers
    0.99
    modifier
    0.98
    Modifiers
    0.95
     Qualifier
    0.93
    Activations Density 0.346%

    No Known Activations