© 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. 12606
    Prev
    Next
    INDEX
    Explanations

    phrases related to workplace ergonomics

    oai_token-act-pair · gemini-2.0-flash

    periods

    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
    IonicModule
    -0.68
    ")){
    -0.68
    AddTagHelper
    -0.65
    UnknownFields
    -0.63
     GenerationType
    -0.63
    ParallelGroup
    -0.60
    exitRule
    -0.57
    WebVitals
    -0.57
    VersionUID
    -0.56
    complexContent
    -0.56
    POSITIVE LOGITS
    Transcription
    0.42
    GIH
    0.42
     otomatig
    0.41
    tillinger
    0.41
     Aufenthalt
    0.40
     ergonomics
    0.40
    乙女
    0.39
     habido
    0.39
    Carcinogenicity
    0.38
     Guild
    0.38
    Activations Density 0.819%

    No Known Activations