© 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. 3162
    Prev
    Next
    INDEX
    Explanations

    words related to the chemical process of dispersion, and some medical words, likely due to a correlation in the training data.

    oai_token-act-pair · gemini-2.0-flash

    scientific and chemical contexts

    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
    bootstrapcdn
    -0.56
     Artem
    -0.52
    wixt
    -0.52
    Marshaller
    -0.52
     surla
    -0.50
     anſ
    -0.49
     newly
    -0.48
    icanos
    -0.47
    Xna
    -0.47
     valentín
    -0.47
    POSITIVE LOGITS
     continúas
    0.54
    GEBURTSDATUM
    0.49
    ⓧ
    0.49
    enumi
    0.48
    цездатний
    0.48
    UnitTesting
    0.47
    ValueGenerated
    0.47
    anasia
    0.45
    ivably
    0.45
    bnf
    0.45
    Activations Density 9.952%

    No Known Activations