© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9453
    Prev
    Next
    INDEX
    Explanations

    disclosures related to consulting and research support, especially in the context of medical companies

    oai_token-act-pair · gemini-2.0-flash

    consultant

    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
    AndEndTag
    -0.65
    writeFieldEnd
    -0.59
    帖最后由
    -0.58
    IsMutable
    -0.57
    SuppressMessage
    -0.57
     MenuView
    -0.57
    SharedDtor
    -0.57
    MENAFN
    -0.56
     personnelle
    -0.56
     SqlDbType
    -0.55
    POSITIVE LOGITS
    makeText
    0.53
    basicConfig
    0.46
     eorum
    0.45
     متعلقه
    0.45
    auce
    0.45
    Eksterne
    0.44
     lisäksi
    0.44
    ACJA
    0.43
     eius
    0.42
    はじめに
    0.42
    Activations Density 1.492%

    No Known Activations