© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13122
    Prev
    Next
    INDEX
    Explanations

    words related to job advertisements, recruitment, and hourly compensation

    oai_token-act-pair · gemini-2.0-flash

    job openings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     seats
    -0.72
     seat
    -0.72
     Spots
    -0.69
    spots
    -0.68
     spots
    -0.67
     Balt
    -0.67
     AssemblyCompany
    -0.64
    Spots
    -0.63
    seats
    -0.63
     spot
    -0.63
    POSITIVE LOGITS
     Normdatei
    0.48
    MouseAdapter
    0.45
     maail
    0.45
    wpi
    0.44
     ***
    0.44
    addPreferredGap
    0.43
    Rujukan
    0.42
     libremente
    0.42
    ************
    0.42
     ого
    0.42
    Activations Density 22.316%

    No Known Activations