© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2156
    Prev
    Next
    INDEX
    Explanations

    words related to medical procedures, the etymology of the words or words ending in "borne".

    oai_token-act-pair · gemini-2.0-flash

    diseases and art

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ItemBackground
    -0.58
    WriteTagHelper
    -0.56
    makeText
    -0.55
     dolorosa
    -0.52
    IsContent
    -0.49
    jewództ
    -0.48
    klare
    -0.47
    Checker
    -0.46
    所在
    -0.45
    وردار
    -0.45
    POSITIVE LOGITS
     كومونز
    0.78
     متعلقه
    0.71
     MutableLiveData
    0.64
    owań
    0.64
     appartamento
    0.62
    ExtendWith
    0.61
    hikari
    0.60
    \|\
    0.60
    ècie
    0.59
     fugitive
    0.58
    Activations Density 7.240%

    No Known Activations