© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12147
    Prev
    Next
    INDEX
    Explanations

    code, filepaths, and structured formatting such as lists and tables

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     protoimpl
    -0.59
     AssemblyProduct
    -0.51
     typelib
    -0.49
    mány
    -0.47
    GroupLayout
    -0.46
    IfNeeded
    -0.45
    BASELINE
    -0.42
    unnitel
    -0.40
    läufe
    -0.40
     internal
    -0.40
    POSITIVE LOGITS
    TagMode
    0.67
    IntoConstraints
    0.66
    )");
    0.65
    #+#
    0.65
     GenerationType
    0.64
    AnimationsModule
    0.62
    '},
    0.61
    NOPQRST
    0.60
     []),
    0.60
     transférez
    0.57
    Activations Density 20.742%

    No Known Activations