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. 831
    Prev
    Next
    INDEX
    Explanations

    identifiers for genes and proteins

    oai_token-act-pair · gemini-2.0-flash

    period or letter "B"

    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
     myſelf
    -0.73
     faſt
    -0.71
     raiſ
    -0.65
     pleaſure
    -0.64
     ſta
    -0.64
     fevere
    -0.63
     poffe
    -0.63
     itſelf
    -0.63
     reaſon
    -0.60
     fallu
    -0.60
    POSITIVE LOGITS
     resourceCulture
    0.76
     ModelExpression
    0.50
    amb
    0.48
    出版年
    0.46
    Abitanti
    0.45
    verwijspagina
    0.44
    subsection
    0.44
     ostavi
    0.43
    InputTagHelper
    0.43
     BoxDecoration
    0.43
    Activations Density 2.119%

    No Known Activations