© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11299
    Prev
    Next
    INDEX
    Explanations

    instances of agreement after an initial statement

    oai_token-act-pair · gemini-2.0-flash

    Conversational acknowledgements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    verwijspagina
    -0.69
    клопе
    -0.66
     utafitiHapana
    -0.65
    AddTagHelper
    -0.61
    เจ
    -0.57
    tabPage
    -0.56
    rigkeit
    -0.54
     AssemblyVersion
    -0.54
    ")){
    -0.53
    lierten
    -0.53
    POSITIVE LOGITS
    AuthProvider
    0.56
     mijne
    0.53
     zelve
    0.53
     bianchi
    0.52
     autorytatywna
    0.51
     dudes
    0.49
     Majefty
    0.49
    InfoWindow
    0.48
    rawtypes
    0.48
    riwal
    0.48
    Activations Density 0.598%

    No Known Activations