© 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. 6447
    Prev
    Next
    INDEX
    Explanations

    vocabulary that's specific to scientific studies, particularly in cell biology and molecular biology, encompassing experimental procedures, proteins, and signaling pathways.

    oai_token-act-pair · gemini-2.0-flash

    biomedical research

    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
     <=",
    -0.73
     propOrder
    -0.71
    )))),
    -0.62
     الاطلاع
    -0.58
     >=",
    -0.58
    AddTagHelper
    -0.57
    rungsseite
    -0.57
     متعلقه
    -0.52
    "]];
    -0.52
    oredCriteria
    -0.50
    POSITIVE LOGITS
     nakalista
    0.63
     Banach
    0.56
     énergétique
    0.53
     NSMutable
    0.53
     ioutil
    0.51
     jäm
    0.50
     timp
    0.50
     méta
    0.50
     typelib
    0.50
    出版年
    0.49
    Activations Density 6.179%

    No Known Activations