© 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. 1537
    Prev
    Next
    INDEX
    Explanations

    places and their roles/occupants

    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
     airline
    0.36
     ########
    0.35
    addAttribute
    0.35
    ণী
    0.34
    дно
    0.33
     scratch
    0.33
    因素
    0.33
    postdata
    0.32
     제조
    0.32
    *******
    0.32
    POSITIVE LOGITS
     employees
    0.53
     managers
    0.52
    経営
    0.51
    goers
    0.51
     ஊழிய
    0.51
    employees
    0.50
    ध्यक्ष
    0.50
     karyawan
    0.49
    Employees
    0.48
     owner
    0.48
    Activations Density 0.172%

    No Known Activations