© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193877
    Prev
    Next
    INDEX
    Explanations

    qualifiers and intensifiers

    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_15_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
     recib
    0.38
     Strength
    0.37
     Rezept
    0.37
     πισ
    0.36
     Proficiency
    0.36
     முதலில்
    0.35
    nyc
    0.35
     Headline
    0.35
    }=
    0.34
     Insp
    0.34
    POSITIVE LOGITS
    اد
    0.38
    اظ
    0.36
    ially
    0.36
    скопа
    0.36
    ມ
    0.35
     semantics
    0.35
    ə
    0.34
    ศาสตร์
    0.34
     shim
    0.34
    cua
    0.34
    Activations Density 0.052%

    No Known Activations