© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15063
    Prev
    Next
    INDEX
    Explanations

    references to American politics, elections, and politicians

    oai_token-act-pair · gemini-2.0-flash

    leadership positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     reinvest
    -0.50
    getFont
    -0.47
    CreateModel
    -0.46
    '},
    -0.45
    }
    -0.45
     Marín
    -0.44
    coltura
    -0.43
    ární
    -0.42
     }>
    -0.41
    \">\
    -0.41
    POSITIVE LOGITS
    phosa
    0.71
    InjectAttribute
    0.69
    دانشنامهٔ
    0.67
    Geplaatst
    0.65
    newArrayList
    0.65
    новништво
    0.64
    SaveChangesAsync
    0.64
    
    0.64
    bajo
    0.63
    adaptiveStyles
    0.62
    Activations Density 1.016%

    No Known Activations