© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6180
    Prev
    Next
    INDEX
    Explanations

    words related to publications, especially books or films

    oai_token-act-pair · gemini-2.0-flash

    Book collections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     written
    -0.50
     tác
    -0.47
     books
    -0.47
     bestseller
    -0.44
     novel
    -0.44
    不起
    -0.43
     écrit
    -0.43
    written
    -0.42
     AssemblyProduct
    -0.42
     adaptation
    -0.42
    POSITIVE LOGITS
    Personensuche
    1.05
     useDispatch
    0.80
    matchCondition
    0.74
     MenuView
    0.73
     يتيمه
    0.71
    %)$
    0.70
     Wikispecies
    0.69
    Smarty
    0.68
     snippetHide
    0.68
     Exacts
    0.66
    Activations Density 1.969%

    No Known Activations