© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 201059
    Prev
    Next
    INDEX
    Explanations

    say "encia" 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_50_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
    imid
    0.39
    modes
    0.39
    lation
    0.39
     configs
    0.38
     लेट
    0.38
    oprene
    0.38
    燹
    0.38
    ましい
    0.38
    etí
    0.37
     nonzero
    0.36
    POSITIVE LOGITS
    der
    0.43
    ja
    0.40
    S
    0.39
    Sto
    0.38
    𝑆
    0.38
     り
    0.38
     corneal
    0.38
    زاده
    0.38
    jede
    0.37
    Rajas
    0.37
    Activations Density 0.001%

    No Known Activations