© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5348
    Prev
    Next
    INDEX
    Explanations

    code-like elements, specifically, parts of Java code related to a class definition including comments with author, public class name, override

    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_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     vectorielles
    -0.47
     Efq
    -0.46
     refroid
    -0.43
     tartalomajánló
    -0.42
     hinweg
    -0.40
     imprimée
    -0.39
    principalColumn
    -0.39
     dépens
    -0.38
    Удачи
    -0.38
     Theſe
    -0.38
    POSITIVE LOGITS
    <bos>
    0.83
    cus
    0.42
    GraphicsUnit
    0.42
    ніципа
    0.42
    MathML
    0.42
    uka
    0.41
    ineno
    0.39
    assen
    0.39
    res
    0.39
    ponses
    0.39
    Activations Density 0.306%

    No Known Activations