© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 422
    Prev
    Next
    INDEX
    Explanations

    German words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     È
    0.20
    ਛ
    0.20
    િમ
    0.20
     strut
    0.20
     métro
    0.19
    Ĭ
    0.19
     Προ
    0.19
    ਇ
    0.19
    ল্যান্ড
    0.19
     อิน
    0.19
    POSITIVE LOGITS
     v
    0.17
     preponderance
    0.16
     z
    0.16
     бонус
    0.16
    `
    0.16
     опу
    0.15
     indulgence
    0.15
    igens
    0.15
     сложно
    0.15
     k
    0.15
    Activations Density 0.027%

    No Known Activations