© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14238
    Prev
    Next
    INDEX
    Explanations

    sentences discussing actions taken by groups or governments through use of the word "would", "will", "announce", or "decide"

    oai_token-act-pair · gemini-2.0-flash

    would

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    IntoConstraints
    -0.61
     GenerationType
    -0.59
     ligiloj
    -0.58
    Personendaten
    -0.58
    tagext
    -0.57
    DotNetBar
    -0.57
    IndentedString
    -0.57
    exitRule
    -0.50
     wireType
    -0.50
    AnchorStyles
    -0.50
    POSITIVE LOGITS
    ****/
    0.56
     argento
    0.55
     getHeight
    0.54
    nitten
    0.52
     Clique
    0.52
     CURIAM
    0.50
     etched
    0.50
     dź
    0.49
     dimensional
    0.49
    letin
    0.49
    Activations Density 1.486%

    No Known Activations