© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6030
    Prev
    Next
    INDEX
    Explanations

    words relating to crime, victims, and societal issues.

    oai_token-act-pair · gemini-2.0-flash

    Meaning "belong"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     
    -0.54
     r
    -0.52
     can
    -0.52
     cui
    -0.50
     w
    -0.49
     D
    -0.48
     has
    -0.48
     t
    -0.48
     d
    -0.47
     in
    -0.45
    POSITIVE LOGITS
     belonged
    1.22
     belong
    1.11
     belongs
    1.00
     pertenece
    0.95
     pertenecen
    0.94
     bershka
    0.89
     ProtoMessage
    0.89
     appartiennent
    0.85
    InputBorder
    0.84
     apparti
    0.82
    Activations Density 3.642%

    No Known Activations