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. 10230
    Prev
    Next
    INDEX
    Explanations

    sentences describing time spent doing something

    oai_token-act-pair · gemini-2.0-flash

    spend

    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
    SourceChecksum
    -1.16
     Normdatei
    -1.02
    astéroïdes
    -0.93
     متعلقه
    -0.89
    Jeografia
    -0.81
     NUKAT
    -0.79
    HasAnnotation
    -0.76
    canestro
    -0.75
    +#+#
    -0.73
    :✨
    -0.71
    POSITIVE LOGITS
     considerable
    0.51
     less
    0.46
     four
    0.43
     approx
    0.43
    理
    0.42
     approximately
    0.41
     hundreds
    0.41
     nearly
    0.40
     several
    0.40
     shavings
    0.40
    Activations Density 5.589%

    No Known Activations