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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10249
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical jargon, particularly related to Docker and Visual Studio

    oai_token-act-pair · gemini-2.0-flash

    local server environment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    bootstrapcdn
    -0.79
    WebElementEntity
    -0.72
    IBOutlet
    -0.72
    ISupport
    -0.69
    GEBURTSDATUM
    -0.69
    interopRequire
    -0.68
    posables
    -0.66
    +#+#
    -0.60
    OrNil
    -0.60
    UnknownFieldSet
    -0.58
    POSITIVE LOGITS
     local
    1.45
    local
    1.34
    Local
    1.26
     Local
    1.23
     LOCAL
    1.19
     locally
    1.16
    LOCAL
    1.15
    locally
    1.05
     Locally
    1.05
     locals
    1.03
    Activations Density 2.342%

    No Known Activations