© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202537
    Prev
    Next
    INDEX
    Explanations

    salary research for roles

    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_37_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
    肘
    0.39
    }^
    0.38
    囘
    0.38
     contradictory
    0.38
     трево
    0.38
    planatory
    0.37
     theirs
    0.37
    ൭
    0.37
     requer
    0.37
     Panc
    0.37
    POSITIVE LOGITS
    Chief
    0.38
     hired
    0.37
    igo
    0.37
    ettek
    0.37
     Workforce
    0.36
     sao
    0.36
     sélectionnés
    0.36
    िखर
    0.35
    umar
    0.35
    িসি
    0.35
    Activations Density 0.001%

    No Known Activations