© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9663
    Prev
    Next
    INDEX
    Explanations

    references to US foreign policy

    oai_token-act-pair · gemini-2.0-flash

    State

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    TagMode
    -0.74
     TestBed
    -0.70
     AssemblyTitle
    -0.68
     lenker
    -0.66
     MainAxisSize
    -0.65
    ラク
    -0.63
    ApiModel
    -0.61
    RenderAtEndOf
    -0.60
    RunAsync
    -0.58
    shadowOpacity
    -0.58
    POSITIVE LOGITS
     State
    1.86
    State
    1.59
     STATE
    1.27
    STATE
    1.05
     Estado
    0.89
    state
    0.82
     state
    0.73
     Staat
    0.73
    Estado
    0.69
    getState
    0.66
    Activations Density 2.405%

    No Known Activations