© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12588
    Prev
    Next
    INDEX
    Explanations

    employment contracts and security

    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_13_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
    es
    0.39
     NIG
    0.38
     дорогу
    0.38
    ﺖ
    0.37
    म
    0.36
    ឮ
    0.36
     rifer
    0.35
     kina
    0.35
     MUI
    0.34
     NAA
    0.34
    POSITIVE LOGITS
    Type
    0.43
    >(&
    0.34
    Copy
    0.34
    Contract
    0.34
     Type
    0.33
     tenant
    0.33
     contract
    0.33
     suble
    0.32
     type
    0.31
     سكان
    0.31
    Activations Density 0.062%

    No Known Activations