© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11925
    Prev
    Next
    INDEX
    Explanations

    variables and formulas in scientific/technical documents, possibly related to chemical compounds and processes

    oai_token-act-pair · gemini-2.0-flash

    chemistry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     CreateTagHelper
    -1.21
     jspb
    -1.08
    featureID
    -1.06
    SourceChecksum
    -1.05
     Lightboxes
    -1.02
    存于互联网档案馆
    -0.98
    styleType
    -0.98
     متعلقه
    -0.98
    fjspx
    -0.97
    AddTagHelper
    -0.96
    POSITIVE LOGITS
    :
    0.55
     n
    0.51
     N
    0.48
    ,
    0.45
     t
    0.43
    -
    0.41
     kap
    0.40
     Hol
    0.40
     nh
    0.40
    print
    0.40
    Activations Density 2.529%

    No Known Activations