© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207062
    Prev
    Next
    INDEX
    Explanations

    say "s" 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_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     austen
    0.38
     palin
    0.38
    <0x1D>
    0.38
     CPD
    0.37
    䢍
    0.37
    䅛
    0.37
     Torque
    0.37
    <0x1C>
    0.37
    CRC
    0.37
     hb
    0.36
    POSITIVE LOGITS
     sewer
    2.64
     Sewer
    2.41
     sewers
    2.36
     sewerage
    2.14
     sewage
    2.00
    Sew
    1.97
     Sew
    1.91
     sew
    1.86
     Sewage
    1.86
     канализа
    1.84
    Activations Density 0.001%

    No Known Activations