© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13317
    Prev
    Next
    INDEX
    Explanations

    the word "Western" in a variety of contexts

    oai_token-act-pair · gemini-2.0-flash

    Western

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     betweenstory
    -0.63
    ########.
    -0.61
    ContentAsync
    -0.60
     Dictionnaire
    -0.59
    enumii
    -0.59
    illai
    -0.58
    참고
    -0.58
    kování
    -0.57
    ButtonModule
    -0.55
     licked
    -0.55
    POSITIVE LOGITS
    antemente
    0.50
     שוליים
    0.46
     bords
    0.45
     merit
    0.43
     mérite
    0.42
    HEM
    0.42
    ohol
    0.41
    urization
    0.40
     gefeiert
    0.40
    вік
    0.40
    Activations Density 0.919%

    No Known Activations