© 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. 212632
    Prev
    Next
    INDEX
    Explanations

    same face, locked, pointing

    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
    Negative Logits
    ranges
    0.38
    Windows
    0.38
     коммуна
    0.38
     பெறும்
    0.34
    サ
    0.34
    ]$
    0.34
     from
    0.34
    range
    0.33
    Ranges
    0.33
     Ranges
    0.33
    POSITIVE LOGITS
    ﺑ
    0.38
     proces
    0.37
     სახელმწიფ
    0.37
    銥
    0.37
     altern
    0.37
    AnalyzeAction
    0.37
    穵
    0.36
    연출
    0.36
     onderzoek
    0.36
     нового
    0.35
    Activations Density 0.002%

    No Known Activations