© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2336
    Prev
    Next
    INDEX
    Explanations

    words related to medicine, health, and treatment

    oai_token-act-pair · gemini-2.0-flash

    history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Obrázky
    -0.62
    KommentareTeilen
    -0.61
    ⓘ
    -0.60
    HomeAsUp
    -0.59
    ruptedException
    -0.59
    PasswordField
    -0.58
    GOTREF
    -0.58
    entary
    -0.58
     URL
    -0.57
    GRANTED
    -0.57
    POSITIVE LOGITS
    fhir
    0.45
    føre
    0.41
    +#+#
    0.40
    Välislingid
    0.40
     patients
    0.40
     препратки
    0.39
     patient
    0.38
    fromnode
    0.38
    TypedDataSet
    0.38
    nale
    0.38
    Activations Density 2.699%

    No Known Activations