© 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. 13722
    Prev
    Next
    INDEX
    Explanations

    technical terms found in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    graphs

    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
    Personensuche
    -0.58
     Heiden
    -0.56
    TagHelpers
    -0.53
    ivir
    -0.50
    chinen
    -0.50
     Populations
    -0.50
     виправивши
    -0.49
     '\\;'
    -0.48
    "}")
    -0.47
     tà
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.61
    RegistryLite
    0.60
     AppCompatTheme
    0.57
     gynnwys
    0.54
     ikiwa
    0.54
    ñora
    0.54
    Tembelea
    0.54
    lccn
    0.51
    存于互联网档案馆
    0.50
    oa̍t
    0.50
    Activations Density 7.348%

    No Known Activations