© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6020
    Prev
    Next
    INDEX
    Explanations

    salary information

    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_39_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
    ovician
    0.39
    attractive
    0.38
    ⭑
    0.38
     Maximus
    0.36
    sent
    0.36
     graces
    0.36
    send
    0.35
     explored
    0.35
     пра
    0.35
    ractive
    0.35
    POSITIVE LOGITS
     છો
    0.41
     ജില്ല
    0.40
    ptic
    0.38
    分離
    0.38
    寿
    0.38
    acil
    0.37
     Dijon
    0.37
    许可证
    0.37
    Anne
    0.36
     Acet
    0.36
    Activations Density 0.002%

    No Known Activations