© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13519
    Prev
    Next
    INDEX
    Explanations

    language related to health and well-being on a broad, societal scale

    oai_token-act-pair · gemini-2.0-flash

    Technical documents and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Dtor
    -0.61
    SourceChecksum
    -0.59
    enumi
    -0.58
    Convey
    -0.52
     mentioned
    -0.51
     consultato
    -0.51
     Ghi
    -0.50
    area
    -0.50
     الدولى
    -0.49
    ChildIndex
    -0.49
    POSITIVE LOGITS
     nonatomic
    0.69
    classnames
    0.58
    complexContent
    0.58
    nonatomic
    0.55
    XtraEditors
    0.53
    batis
    0.53
    ponym
    0.52
    baomidou
    0.52
    <%=
    0.51
    lüğ
    0.51
    Activations Density 2.520%

    No Known Activations