© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7222
    Prev
    Next
    INDEX
    Explanations

    religious texts and concepts, especially from the Bible.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    الإنجليزية
    -0.43
     com
    -0.40
    BAT
    -0.40
     बीच
    -0.39
    s
    -0.38
    ,
    -0.38
    ud
    -0.38
    com
    -0.38
    ba
    -0.37
    be
    -0.37
    POSITIVE LOGITS
     myſelf
    0.93
    InjectAttribute
    0.93
     ſche
    0.85
    DeleteBehavior
    0.83
     ſind
    0.82
     becauſe
    0.81
     pleaſure
    0.80
    ]--;
    0.79
     Majefty
    0.79
     ſhe
    0.76
    Activations Density 1.765%

    No Known Activations