© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12846
    Prev
    Next
    INDEX
    Explanations

    hexidecimal color codes and years, and sometimes "current"

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    HasAnnotation
    -0.53
    TemporalType
    -0.52
    ruptcy
    -0.52
    otine
    -0.50
    смотра
    -0.50
    XmlAccessType
    -0.50
     AspNetCore
    -0.49
    teenth
    -0.48
    ädie
    -0.47
    opsida
    -0.47
    POSITIVE LOGITS
     estekak
    0.75
    apnews
    0.75
    netbeans
    0.65
    UnknownFields
    0.63
     nahilalakip
    0.63
     nakalista
    0.60
     Ause
    0.59
    extendable
    0.57
     prêts
    0.56
    例句
    0.55
    Activations Density 1.877%

    No Known Activations