© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11556
    Prev
    Next
    INDEX
    Explanations

    words referring to non-player characters in a game and also words related to being thankful

    oai_token-act-pair · gemini-2.0-flash

    Game bosses and gratitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     catalog
    -0.71
     liked
    -0.69
     loved
    -0.67
     catalogue
    -0.63
     Liked
    -0.62
     buff
    -0.60
     catalogs
    -0.60
    帖最后由
    -0.58
     Catalog
    -0.57
     catalogo
    -0.56
    POSITIVE LOGITS
    PreferredItem
    0.83
    awtextra
    0.83
    bukkit
    0.63
    onViewCreated
    0.60
    KommentareTeilen
    0.59
    UserScript
    0.56
     disambiguazione
    0.55
    orianCalendar
    0.54
    adaptiveStyles
    0.53
    MathML
    0.52
    Activations Density 1.318%

    No Known Activations