© 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. 10951
    Prev
    Next
    INDEX
    Explanations

    C/C++, Java, and PHP code

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
    ίος
    -0.51
    CppCodeGen
    -0.50
    #+#
    -0.50
    تقاوى
    -0.49
    GLFW
    -0.49
    ```
    -0.48
     Signalez
    -0.47
    osit
    -0.46
     Società
    -0.45
    Pyx
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.73
    enapa
    0.60
    SUFFIX
    0.58
     avoient
    0.56
    Хьажоргаш
    0.56
    arod
    0.55
    TypedDataSet
    0.55
     Creature
    0.54
    suff
    0.53
     GenerationType
    0.53
    Activations Density 1.923%

    No Known Activations