© 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. 13525
    Prev
    Next
    INDEX
    Explanations

    instances of formal language constructs such as laws, experiments, and mathematical expressions

    oai_token-act-pair · 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
    <bos>
    -0.77
    PutMapping
    -0.49
    ￣)
    -0.47
    zium
    -0.46
    usel
    -0.46
     case
    -0.45
    utations
    -0.45
    AddTagHelper
    -0.45
     swore
    -0.44
    sitions
    -0.44
    POSITIVE LOGITS
    发表于
    0.75
     }{@
    0.64
     OFDb
    0.63
     Vikipedi
    0.61
     transfieras
    0.59
    новништво
    0.58
     disponibilités
    0.57
     BoxFit
    0.56
    JvmStatic
    0.56
     disambiguazione
    0.55
    Activations Density 10.244%

    No Known Activations