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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8058
    Prev
    Next
    INDEX
    Explanations

    text with a religious theme that includes the word 'God', and words associated with faith.

    oai_token-act-pair · gemini-2.0-flash

    God and religion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     quæ
    -0.93
     houſe
    -0.85
     Shakspeare
    -0.85
     Diſ
    -0.83
     Houſe
    -0.82
     Eſ
    -0.81
     ſtate
    -0.79
     laſt
    -0.78
     Италијани
    -0.78
     greateſt
    -0.78
    POSITIVE LOGITS
     His
    0.62
     Me
    0.58
    ,
    0.51
    PMailer
    0.50
     Your
    0.50
     Him
    0.47
    ...
    0.47
     great
    0.47
     and
    0.46
    …
    0.46
    Activations Density 9.186%

    No Known Activations