© 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
    2. Gemma-3-27B-IT
    3. 9-GEMMASCOPE-2-TRANSCODER-262K
    4. 196678
    Prev
    Next
    INDEX
    Explanations

    ICICI Bank, TATA Insurance

    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_9_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
    是
    0.97
    는
    0.87
    posición
    0.82
     विधायकों
    0.79
    achtree
    0.79
     తమ
    0.78
     litigants
    0.77
     viviendas
    0.75
    моль
    0.75
     अंतर्गत
    0.74
    POSITIVE LOGITS
    )
    1.45
     or
    1.13
    CE
    1.06
    A
    1.05
    ,
    1.04
     can
    1.00
    AY
    1.00
    IN
    1.00
    IZA
    0.97
    ;
    0.97
    Activations Density 0.001%

    No Known Activations