© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9330
    Prev
    Next
    INDEX
    Explanations

    words related to medicine, law, and childbirth, particularly in the context of patients, cases, legal frameworks, and medical conditions.

    oai_token-act-pair · gemini-2.0-flash

    temporal conjunctions or phrases

    np_token-act-pair-logits · gpt-4o-mini

    when

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    OGND
    -0.74
     BoxDecoration
    -0.65
    LookAnd
    -0.64
     okuyayım
    -0.61
     transférez
    -0.58
    Pautan
    -0.54
    InvalidProtocol
    -0.54
    borderSide
    -0.52
    photobucket
    -0.51
     Wikimedijinoj
    -0.51
    POSITIVE LOGITS
     when
    1.96
    when
    1.73
     quando
    1.56
     cuando
    1.52
     WHEN
    1.44
     When
    1.41
    When
    1.34
    cuando
    1.34
     когда
    1.34
     lorsqu
    1.30
    Activations Density 3.145%

    No Known Activations