© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149282
    Prev
    Next
    INDEX
    Explanations

    job roles

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    _:
    0.41
     "${
    0.39
    akyat
    0.38
    :@
    0.38
     "@
    0.38
    ²',
    0.38
     "&
    0.38
     चलता
    0.36
     Liabilities
    0.36
     "["
    0.35
    POSITIVE LOGITS
     role
    0.68
     area
    0.68
     world
    0.66
     side
    0.59
    世界
    0.59
    Role
    0.56
     mundo
    0.54
     wereld
    0.53
    role
    0.52
     lado
    0.50
    Activations Density 0.010%

    No Known Activations