© 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-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15264
    Prev
    Next
    INDEX
    Explanations

    mentions of students, school staff, tournament staff, and professional training staff.

    oai_token-act-pair · gemini-2.0-flash

    students

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Players
    -1.47
     Students
    -1.38
     Patients
    -1.31
     Player
    -1.29
     Voters
    -1.26
     Athletes
    -1.25
     Employees
    -1.25
     Visitors
    -1.22
     Candidates
    -1.20
     Drivers
    -1.19
    POSITIVE LOGITS
     people
    1.01
     young
    0.92
     female
    0.80
     người
    0.79
     younger
    0.75
     individuals
    0.73
     members
    0.72
    ผู้
    0.72
     girl
    0.65
     women
    0.65
    Activations Density 3.780%

    No Known Activations