© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11586
    Prev
    Next
    INDEX
    Explanations

    instances of html div tags and the classname attribute as well as ternary operators

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    QMetaType
    -1.13
    AnimationsModule
    -1.13
     Roskov
    -1.09
     disambiguazione
    -1.09
     ویکی‌پدی
    -1.09
    ंदीखरीदारी
    -1.09
    rrggbb
    -1.05
     nakalista
    -1.05
     CreateTagHelper
    -1.04
     AssemblyCulture
    -1.02
    POSITIVE LOGITS
    @
    0.56
    {
    0.54
    I
    0.51
    C
    0.46
    [
    0.45
    R
    0.44
    L
    0.43
    #
    0.42
    ↵↵
    0.42
    This
    0.41
    Activations Density 3.436%

    No Known Activations