© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41146
    Prev
    Next
    INDEX
    Explanations

    community

    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_22_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
    pèce
    0.39
    Metaxy
    0.39
    resos
    0.38
    水果
    0.38
    entials
    0.37
    ">–
    0.37
    вку
    0.37
    齁
    0.37
    ativ
    0.37
    åll
    0.36
    POSITIVE LOGITS
     rigged
    0.46
     nineteenth
    0.45
     legacy
    0.44
     dham
    0.44
     Ples
    0.44
     swapped
    0.43
     assurances
    0.43
     many
    0.42
     vend
    0.42
     succession
    0.42
    Activations Density 0.008%

    No Known Activations