© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1825
    Prev
    Next
    INDEX
    Explanations

    code keywords defining visibility or scope, and class/method/variable declarations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    expandindo
    -0.75
    MENAFN
    -0.69
    CopyWith
    -0.65
    IntoConstraints
    -0.64
     ब्रेकडाउन
    -0.64
     AttributeSet
    -0.60
     صوتيه
    -0.59
    AnchorStyles
    -0.58
     مرئيه
    -0.56
     Himo
    -0.53
    POSITIVE LOGITS
    atguigu
    0.60
    __":
    0.59
     насељу
    0.57
    AndEndTag
    0.55
    <bos>
    0.54
    InstrumentedTest
    0.53
    AntiForgeryToken
    0.53
    tafogo
    0.51
     Italijani
    0.50
    ReadInt
    0.48
    Activations Density 0.308%

    No Known Activations