© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121664
    Prev
    Next
    INDEX
    Explanations

    can handle massive workloads

    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_27_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
    ရာ
    0.42
     Missing
    0.41
     உரு
    0.39
     Schmid
    0.39
    曛
    0.38
    쌤
    0.38
    秘书
    0.38
    河流
    0.37
     mynd
    0.37
    bursements
    0.37
    POSITIVE LOGITS
    op
    0.46
    if
    0.42
    pe
    0.39
    ov
    0.38
    increment
    0.38
    more
    0.38
    limit
    0.38
     retains
    0.37
    depth
    0.37
    za
    0.37
    Activations Density 0.005%

    No Known Activations