© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6472
    Prev
    Next
    INDEX
    Explanations

    the word "some"

    oai_token-act-pair · gemini-2.0-flash

    some

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    transQ
    -0.58
    SpringBootTest
    -0.57
    oa̍t
    -0.57
    ])));
    -0.54
    //});
    -0.52
    enderror
    -0.52
    ()]);
    -0.51
    )");
    -0.51
    SuspendLayout
    -0.50
     المعيارى
    -0.50
    POSITIVE LOGITS
     kind
    1.19
     sort
    1.07
    kind
    1.04
    Kind
    0.93
     KIND
    0.92
     Kind
    0.90
    sort
    0.83
     type
    0.82
    KIND
    0.72
     kinds
    0.71
    Activations Density 0.300%

    No Known Activations