© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174128
    Prev
    Next
    INDEX
    Explanations

    dwellings and residences

    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_20_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
     boring
    0.37
    beitung
    0.35
     siya
    0.35
    oshi
    0.34
    ClO
    0.33
     tê
    0.33
    牵
    0.33
    
    0.32
     posição
    0.32
     वैश्विक
    0.32
    POSITIVE LOGITS
     Novosibirsk
    0.40
    шении
    0.39
    蟳
    0.38
     koul
    0.38
    <li>
    0.37
     potrav
    0.37
    मिन
    0.37
     nutric
    0.36
     મોટી
    0.36
     ਕੀਤੀ
    0.36
    Activations Density 0.002%

    No Known Activations