© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8847
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on a variety of words, but with a certain bias towards food ingredients, place names, location names, and Japanese text

    oai_token-act-pair · gemini-2.0-flash

    Technical and foreign text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     дописавши
    -0.52
    IntoConstraints
    -0.52
    sidemargin
    -0.51
     spesies
    -0.50
    цездатний
    -0.49
     Roskov
    -0.49
     Holiness
    -0.48
     UIFont
    -0.48
     SqlParameter
    -0.47
     heureuse
    -0.47
    POSITIVE LOGITS
     testSet
    0.55
     كومونز
    0.53
    ีย
    0.51
    zbęd
    0.49
    muster
    0.49
    einander
    0.48
    NOPQRST
    0.47
    KommentareTeilen
    0.47
    Koordinaten
    0.47
    WebpackPlugin
    0.46
    Activations Density 1.801%

    No Known Activations