© 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. 10675
    Prev
    Next
    INDEX
    Explanations

    words related to the US military

    oai_token-act-pair · gemini-2.0-flash

    Military units

    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
    Personendaten
    -0.67
    MigrationBuilder
    -0.64
    itinéraire
    -0.63
     initComponents
    -0.60
     AttributeSet
    -0.59
    FXML
    -0.57
     defaultstate
    -0.54
    hasMoreElements
    -0.53
     Himo
    -0.53
     ujednoznacz
    -0.52
    POSITIVE LOGITS
    AndEndTag
    0.63
     PublicKey
    0.62
    lgari
    0.56
     ddelweddau
    0.52
    gantung
    0.50
    .*")]
    0.48
     Reſ
    0.47
     ТА
    0.47
     LIBR
    0.46
    EndContext
    0.46
    Activations Density 0.686%

    No Known Activations