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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14755
    Prev
    Next
    INDEX
    Explanations

    PHP code syntax related to using methods and properties of objects

    oai_token-act-pair · gemini-2.0-flash

    Code/foreign language

    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
    TargetException
    -0.63
    ftagPool
    -0.62
    Географи
    -0.60
    HandlerContext
    -0.58
     estekak
    -0.57
     kasarigan
    -0.57
    onomi
    -0.54
    DoubleQuotes
    -0.53
    OGND
    -0.52
    Enllaces
    -0.51
    POSITIVE LOGITS
     resourceCulture
    0.50
    izaciones
    0.48
    Passcode
    0.46
    GEBURTSDATUM
    0.45
     itself
    0.45
    MEAN
    0.44
    ütfen
    0.44
    ędzy
    0.44
    колко
    0.44
    úsqueda
    0.44
    Activations Density 0.797%

    No Known Activations