© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4320
    Prev
    Next
    INDEX
    Explanations

    HTML attributes or elements related to styling or scripting, often involving the terms "class", "id", or "value"

    oai_token-act-pair · gemini-2.0-flash

    HTML attributes

    np_token-act-pair-logits · gpt-4o-mini

    id

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     T
    -0.68
     H
    -0.56
     t
    -0.54
     "
    -0.49
    <eos>
    -0.48
     I
    -0.48
    mo
    -0.48
     Y
    -0.47
     '
    -0.47
    urio
    -0.47
    POSITIVE LOGITS
    énario
    0.91
    ftagPool
    0.82
     itſelf
    0.81
     Efq
    0.79
     ―――――
    0.78
     myſelf
    0.77
     raiſ
    0.76
    ſelves
    0.74
    LookAnd
    0.72
     Савезне
    0.69
    Activations Density 0.247%

    No Known Activations