© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15973
    Prev
    Next
    INDEX
    Explanations

    the word "pool"

    oai_token-act-pair · gemini-2.0-flash

    pool

    np_max-act · gemini-2.0-flash

    ▁pool

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     in
    -0.70
     on
    -0.65
     and
    -0.62
     ||
    -0.59
     ‘
    -0.54
     a
    -0.53
     Por
    -0.52
    ly
    -0.51
     of
    -0.50
     or
    -0.50
    POSITIVE LOGITS
     resourceCulture
    1.31
    sizeCache
    1.28
     pleaſure
    1.27
     Theſe
    1.27
     becauſe
    1.23
     Houſe
    1.20
     doubtnut
    1.20
     whoſe
    1.19
     Anſ
    1.18
     purpoſe
    1.18
    Activations Density 1.114%

    No Known Activations