© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14051
    Prev
    Next
    INDEX
    Explanations

    words and phrases that relate to internal cognitive processes, like thinking, feeling, or speaking.

    oai_token-act-pair · gemini-2.0-flash

    Thoughts/Speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     متعلقه
    -0.78
    RegressionTest
    -0.77
    FunctionFlags
    -0.73
    حياته
    -0.72
    seits
    -0.66
    }{*}{
    -0.65
    MergeFrom
    -0.65
    ">—
    -0.64
    Coordonnées
    -0.63
    twimg
    -0.63
    POSITIVE LOGITS
     NUnit
    0.54
    س
    0.47
    Med
    0.46
    WriteAttribute
    0.46
    ↵
    0.46
     retrospect
    0.45
    UnitTesting
    0.45
     saying
    0.44
    nextProps
    0.43
     mengadakan
    0.43
    Activations Density 1.348%

    No Known Activations