© 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. 7330
    Prev
    Next
    INDEX
    Explanations

    code-related words like "public", "private", "Calendar", and code structures or parts of those

    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
    MergeFrom
    -0.79
    flink
    -0.54
    Viitteet
    -0.52
    antía
    -0.50
     ej
    -0.49
    Tril
    -0.48
    bibitem
    -0.48
     EClass
    -0.48
    DropTable
    -0.47
    ometro
    -0.47
    POSITIVE LOGITS
    ⓧ
    0.83
     Signalez
    0.70
     AssemblyCulture
    0.68
    +#+#
    0.62
    __).
    0.57
    Хьажоргаш
    0.55
    ImageContext
    0.54
    DockStyle
    0.53
    InjectAttribute
    0.53
    ✨:
    0.52
    Activations Density 2.002%

    No Known Activations