© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 16030
    Prev
    Next
    INDEX
    Explanations

    the names of people speaking at some event

    oai_token-act-pair · gemini-2.0-flash

    giving speeches

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    UnitTesting
    -0.60
     betweenstory
    -0.60
     CreateTagHelper
    -0.58
     BIBSYS
    -0.54
    ItemBackground
    -0.54
     Metacritic
    -0.54
    ետ
    -0.53
     متعلقه
    -0.52
    וויק
    -0.52
    figer
    -0.50
    POSITIVE LOGITS
     speech
    1.55
     speeches
    1.42
     address
    1.41
     addresses
    1.35
     speaker
    1.33
     speakers
    1.31
     speaking
    1.29
     Address
    1.23
     Speech
    1.21
    speech
    1.21
    Activations Density 1.349%

    No Known Activations