© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12966
    Prev
    Next
    INDEX
    Explanations

    words associated with military service, especially positive attributes and awards

    oai_token-act-pair · gemini-2.0-flash

    Army, military

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     prioritized
    -0.47
     économiques
    -0.45
    Λ
    -0.45
     Garanti
    -0.44
    Or
    -0.44
    booked
    -0.43
    trá
    -0.43
    oba
    -0.43
    ex
    -0.42
    CE
    -0.42
    POSITIVE LOGITS
     resourceCulture
    0.94
     المعيارى
    0.91
     समीक्षाओं
    0.81
     متعلقه
    0.78
    ItemBackground
    0.74
     transfieras
    0.67
     CanadaChoose
    0.67
    AndEndTag
    0.66
    abestanden
    0.65
     esternos
    0.65
    Activations Density 0.831%

    No Known Activations