© 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. 14811
    Prev
    Next
    INDEX
    Explanations

    words that relate to political violence and governmental authority

    oai_token-act-pair · gemini-2.0-flash

    government/military installations

    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
     propOrder
    -0.89
    Personendaten
    -0.88
    Datuak
    -0.86
     NSCoder
    -0.79
     intptr
    -0.77
    GEBURTSDATUM
    -0.76
    TypedDataSet
    -0.75
    CloseOperation
    -0.75
    DockStyle
    -0.74
    ⓧ
    -0.74
    POSITIVE LOGITS
     orígenes
    0.43
    ignal
    0.37
     origini
    0.36
     mejorado
    0.36
     formación
    0.36
     límites
    0.36
     dominio
    0.36
    欲しい
    0.36
     investir
    0.36
    vo
    0.35
    Activations Density 34.402%

    No Known Activations