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. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12255
    Prev
    Next
    INDEX
    Explanations

    phrases discussing fiscal matters

    oai_token-act-pair · gemini-2.0-flash

    Business and money

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     ſy
    -0.55
    KommentareTeilen
    -0.52
    UnknownFields
    -0.50
     Immobili
    -0.50
     }}$}
    -0.48
    lemmer
    -0.48
     Seal
    -0.48
     елның
    -0.48
    ]};
    -0.48
    immobili
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.82
    antMatchers
    0.68
    EndContext
    0.65
     GenerationType
    0.61
    LookAnd
    0.60
    __*/
    0.60
     kasarigan
    0.60
    matchCondition
    0.59
    ViewImports
    0.59
    HtmlAttribute
    0.58
    Activations Density 2.968%

    No Known Activations