© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4132
    Prev
    Next
    INDEX
    Explanations

    scientific terms or phrases consisting of multiple capitalized letters and numbers, especially those related to biology, chemistry and medicine.

    oai_token-act-pair · gemini-2.0-flash

    Anatomy, medical terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     يتيمه
    -0.68
     ddelweddau
    -0.62
    ANO
    -0.60
    ADE
    -0.51
    ER
    -0.50
    XmlAccessorType
    -0.50
    EN
    -0.48
    staticmethod
    -0.48
    ATO
    -0.47
    ENSA
    -0.46
    POSITIVE LOGITS
     resourceCulture
    0.63
     bezeichneter
    0.57
    setVerticalGroup
    0.56
    iform
    0.54
     umbi
    0.54
    oplasma
    0.53
     Factbook
    0.53
    ophilus
    0.53
    rolid
    0.53
     foramen
    0.52
    Activations Density 22.713%

    No Known Activations