Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 723
    Prev
    Next
    INDEX
    Explanations

    words related to engineering, mechanics, or vehicle modification

    oai_token-act-pair · gemini-2.0-flash

    vertical position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    createClass
    -0.58
    EndContext
    -0.56
     upward
    -0.54
     heights
    -0.54
    URLException
    -0.52
    ()?;
    -0.52
     nakalista
    -0.52
    ähän
    -0.49
    gasus
    -0.49
     height
    -0.48
    POSITIVE LOGITS
     disambiguazione
    0.66
     resourceCulture
    0.54
    jsxFileName
    0.54
    KURZBESCHREIBUNG
    0.54
    twimg
    0.50
     invokingState
    0.49
    EDEFAULT
    0.49
    ckså
    0.48
    InitVars
    0.48
    IsMutable
    0.48
    Activations Density 3.213%

    No Known Activations