© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4364
    Prev
    Next
    INDEX
    Explanations

    words related to employment and creative endeavors, especially in media.

    oai_token-act-pair · gemini-2.0-flash

    artistic careers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     estekak
    -0.85
    oredCriteria
    -0.84
    InitVars
    -0.84
    出版年
    -0.81
    WireFormatLite
    -0.81
     utafitiHapana
    -0.75
     utafiti
    -0.74
    ItemBackground
    -0.73
    Chham
    -0.73
     BrowserModule
    -0.71
    POSITIVE LOGITS
    let
    0.50
     face
    0.49
     Q
    0.46
     bank
    0.45
     điều
    0.44
     key
    0.44
     deal
    0.44
     output
    0.43
     label
    0.43
     q
    0.42
    Activations Density 1.492%

    No Known Activations