© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7669
    Prev
    Next
    INDEX
    Explanations

    the word "sense" (sometimes in the phrase "makes sense")

    oai_token-act-pair · gemini-2.0-flash

    sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Shakspeare
    -0.87
     ་་
    -0.83
     raiſ
    -0.81
     deſt
    -0.81
     EEU
    -0.81
     quæ
    -0.80
     Phry
    -0.78
     Universitaria
    -0.78
     Eskimo
    -0.77
     uſed
    -0.77
    POSITIVE LOGITS
     the
    0.91
    NUMX
    0.80
     Mag
    0.78
    $",
    0.77
     my
    0.74
    mila
    0.72
    "]);
    0.71
    '])
    0.71
    ']))
    0.70
     an
    0.70
    Activations Density 1.412%

    No Known Activations