© 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. 14679
    Prev
    Next
    INDEX
    Explanations

    words relating to religions, political ideologies, and forms of oppression

    oai_token-act-pair · gemini-2.0-flash

    Religion and politics

    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
    脚注の使い方
    -0.81
     field
    -0.77
     fielder
    -0.72
     unterwegs
    -0.71
     Field
    -0.68
     fieldwork
    -0.64
    قایناقلار
    -0.63
    {}",
    -0.63
    withIdentifier
    -0.63
    ازم
    -0.63
    POSITIVE LOGITS
     Chwiliwch
    0.49
     sonno
    0.48
    YPE
    0.40
    manera
    0.39
     líquida
    0.38
     etmeye
    0.38
    ração
    0.37
     naturali
    0.37
    LoadScene
    0.36
     pytest
    0.36
    Activations Density 2.015%

    No Known Activations