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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12723
    Prev
    Next
    INDEX
    Explanations

    HTML input element attributes like "for", "id", and "name"

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     للمعارف
    -1.03
    IntoConstraints
    -0.75
    وعة
    -0.64
     odkazy
    -0.63
     سكانية
    -0.61
     gynhyrchwyd
    -0.56
    ardy
    -0.56
    \{\\
    -0.55
    uttosto
    -0.55
    GetEnumerator
    -0.54
    POSITIVE LOGITS
    IUrlHelper
    0.69
    AddTagHelper
    0.67
    <bos>
    0.66
    GraphicsUnit
    0.63
    tagHelperRunner
    0.59
    utnik
    0.57
    uxxxx
    0.53
    LookAnd
    0.52
    GEBURTSDATUM
    0.51
     EClass
    0.50
    Activations Density 0.533%

    No Known Activations