© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12730
    Prev
    Next
    INDEX
    Explanations

    references or citations of external sources in the text

    oai_token-act-pair · gemini-2.0-flash

    source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     source
    -1.91
     sources
    -1.90
     Sources
    -1.74
     Source
    -1.65
    source
    -1.63
    Sources
    -1.60
    sources
    -1.59
    Source
    -1.53
     SOURCE
    -1.52
     SOURCES
    -1.40
    POSITIVE LOGITS
    
    0.90
    ThroughAttribute
    0.71
    utilisons
    0.67
     surla
    0.66
     Jefus
    0.65
    ñores
    0.65
    complexContent
    0.63
    XmlEnum
    0.63
    LookAnd
    0.62
     Ensino
    0.61
    Activations Density 40.679%

    No Known Activations