© 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. 212694
    Prev
    Next
    INDEX
    Explanations

    Kraftwerk, boloñesa, Bubble Sort

    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
     collega
    0.48
     Daarna
    0.47
    𝙮
    0.46
    чника
    0.45
    ჭ
    0.45
    𝓎
    0.44
     zorgt
    0.44
    ğiniz
    0.43
    ㄆ
    0.43
    OAc
    0.43
    POSITIVE LOGITS
    ad
    0.47
     dialect
    0.46
     silicone
    0.44
     socket
    0.44
     πλή
    0.41
     retrofit
    0.41
     non
    0.40
     centro
    0.40
     grating
    0.40
     rendition
    0.40
    Activations Density 0.000%

    No Known Activations