© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7576
    Prev
    Next
    INDEX
    Explanations

    various characters used in code and mathematics.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -0.84
    awtextra
    -0.61
    resave
    -0.57
    BASEPATH
    -0.53
    arbox
    -0.52
    TagMode
    -0.50
    UnusedPrivate
    -0.50
    SourceChecksum
    -0.48
    divided
    -0.48
     مواليد
    -0.47
    POSITIVE LOGITS
    存于互联网档案馆
    0.59
     onBackPressed
    0.59
     ICF
    0.57
     δὲ
    0.56
     financière
    0.56
    aVar
    0.56
     Ril
    0.56
    rolid
    0.55
     estekak
    0.54
     raiſ
    0.54
    Activations Density 1.613%

    No Known Activations