© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14649
    Prev
    Next
    INDEX
    Explanations

    code snippets containing syntax and keywords from a range of programming languages

    oai_token-act-pair · gemini-2.0-flash

    >>>

    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
    Rng
    -0.52
    empio
    -0.52
    featureID
    -0.50
    WriteTagHelper
    -0.50
    AndEndTag
    -0.50
    IsContent
    -0.49
    <bos>
    -0.48
    OutputType
    -0.48
    ())),
    -0.48
     troppo
    -0.47
    POSITIVE LOGITS
     متعلقه
    0.82
    сылкі
    0.65
    orianCalendar
    0.64
    المناصب
    0.63
    GraphicsUnit
    0.58
    Personendaten
    0.58
    Искәрмәләр
    0.57
    　　[
    0.56
    setVerticalGroup
    0.55
    Kaieteur
    0.54
    Activations Density 0.456%

    No Known Activations