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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8443
    Prev
    Next
    INDEX
    Explanations

    references to God(s) and religious worship

    oai_token-act-pair · gemini-2.0-flash

    say "on"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    
    -0.58
    ribune
    -0.54
    SWR
    -0.50
     defStyle
    -0.49
    Ārējās
    -0.48
    ClientRect
    -0.48
    fgets
    -0.46
    VSS
    -0.44
     recyclerView
    -0.44
    uário
    -0.44
    POSITIVE LOGITS
     upon
    2.77
     UPON
    2.58
    upon
    2.55
     Upon
    2.41
    Upon
    2.28
     vpon
    1.22
     apon
    1.18
     upo
    0.85
     defaultstate
    0.84
     asupra
    0.81
    Activations Density 6.630%

    No Known Activations