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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6763
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the physical attributes of various objects or processes.

    oai_token-act-pair · gemini-2.0-flash

    Evenness and smoothness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     flat
    -0.65
    Smooth
    -0.65
     Smooth
    -0.60
    smooth
    -0.56
    flat
    -0.56
     lisse
    -0.54
     AssemblyProduct
    -0.54
     jspb
    -0.54
     straight
    -0.53
     Straight
    -0.52
    POSITIVE LOGITS
     EconPapers
    0.65
     صوتيه
    0.60
    transQ
    0.55
    NewReader
    0.53
     Funnel
    0.53
    HtmlAttribute
    0.53
    reathe
    0.52
    olum
    0.52
    theless
    0.51
     JADX
    0.51
    Activations Density 16.392%

    No Known Activations