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. 10313
    Prev
    Next
    INDEX
    Explanations

    various types of punctuation intermixed with first and second person pronouns

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
     fédé
    -0.52
     généraux
    -0.48
     embora
    -0.47
     spôso
    -0.46
     étoit
    -0.46
     متحده
    -0.45
     fédéral
    -0.43
    WhereInput
    -0.43
     Himo
    -0.43
     publicitaires
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.66
    jari
    0.66
    verifyException
    0.65
    getDescriptor
    0.63
     ComVisible
    0.61
     it
    0.60
     initComponents
    0.60
     I
    0.57
    ombus
    0.57
    SharedCtor
    0.57
    Activations Density 3.447%

    No Known Activations