© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11751
    Prev
    Next
    INDEX
    Explanations

    words denoting something out of the ordinary

    oai_token-act-pair · gemini-2.0-flash

    odd, strange

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     strange
    -1.69
     odd
    -1.57
     weird
    -1.48
    strange
    -1.41
     unusual
    -1.34
    Strange
    -1.29
     Strange
    -1.24
    unusual
    -1.20
     Odd
    -1.20
     Weird
    -1.18
    POSITIVE LOGITS
    AlterField
    0.73
    ureusement
    0.65
    nerf
    0.61
     resourceCulture
    0.60
     respec
    0.56
    *)((
    0.56
    Pranala
    0.55
    felizmente
    0.54
    _();
    0.54
    mortar
    0.54
    Activations Density 3.697%

    No Known Activations