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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2136
    Prev
    Next
    INDEX
    Explanations

    public officials or city travel

    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_40_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
    CE
    0.40
    漕
    0.39
     Dare
    0.38
     translating
    0.37
     Gaspar
    0.37
    亰
    0.37
     retail
    0.37
    限量
    0.37
    筲
    0.36
    cing
    0.36
    POSITIVE LOGITS
     homogene
    0.39
     tact
    0.39
     vulve
    0.39
    Glare
    0.38
    홧
    0.38
     hồ
    0.36
     takt
    0.36
     chron
    0.35
     efektif
    0.35
     homer
    0.35
    Activations Density 0.014%

    No Known Activations