© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40740
    Prev
    Next
    INDEX
    Explanations

    say "number" phrases

    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_57_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
     sixth
    0.45
    uaries
    0.43
     कुलकर्णी
    0.40
     thirteenth
    0.39
     गार
    0.39
    ₆
    0.38
     Sixth
    0.37
     यूनिक
    0.37
    дового
    0.37
     sixty
    0.37
    POSITIVE LOGITS
    Ten
    0.46
     नाइन
    0.42
     ২০১০
    0.42
     Ten
    0.41
     tub
    0.40
     Bradshaw
    0.39
    九
    0.39
    দশ
    0.38
     ten
    0.38
    institut
    0.38
    Activations Density 0.024%

    No Known Activations