© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11796
    Prev
    Next
    INDEX
    Explanations

    code snippets with CSS styling (specifically, hiding elements) and related discussion

    oai_token-act-pair · gemini-2.0-flash

    hide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    kháu
    -0.69
    ]));
    -0.67
     BoxFit
    -0.65
    });
    -0.65
     CYTHON
    -0.64
    CppCodeGen
    -0.63
    NUMX
    -0.62
     himo
    -0.60
    ggak
    -0.60
     Vuitton
    -0.60
    POSITIVE LOGITS
    IMPORTED
    0.49
    ural
    0.47
     vivement
    0.41
    abestanden
    0.40
    BASELINE
    0.40
     للاسماء
    0.39
    main
    0.38
    惹
    0.38
    賦
    0.37
    洋
    0.36
    Activations Density 0.445%

    No Known Activations