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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7187
    Prev
    Next
    INDEX
    Explanations

    words related to thought, consideration, and opposition, especially the verb "face"

    oai_token-act-pair · gemini-2.0-flash

    dealing with problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     övers
    -0.63
     arbejde
    -0.55
     来自
    -0.54
     love
    -0.53
     work
    -0.51
     trabajo
    -0.49
     suaminya
    -0.47
     esposo
    -0.46
     TextAppearance
    -0.46
     escre
    -0.45
    POSITIVE LOGITS
    Lähteet
    0.82
    حياته
    0.80
    tagext
    0.75
    tonsoft
    0.74
     betweenstory
    0.73
     showbiz
    0.73
    InjectAttribute
    0.72
    saraba
    0.71
    SharedCtor
    0.71
     CreateTagHelper
    0.70
    Activations Density 1.086%

    No Known Activations