Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14648
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with Christian religious belief.

    oai_token-act-pair · gemini-2.0-flash

    salvation

    np_max-act-logits · 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
    Not in Any Lists

    No Comments

    Negative Logits
     mergeFrom
    -0.69
     للمعارف
    -0.63
     Chwiliwch
    -0.54
    ernalia
    -0.54
     souple
    -0.53
    ंदीखरीदारी
    -0.53
    fjspx
    -0.53
    ReusableCell
    -0.51
    principalColumn
    -0.50
     kaarangay
    -0.50
    POSITIVE LOGITS
     saved
    0.82
     justified
    0.75
    saved
    0.73
    KommentareTeilen
    0.65
     Saved
    0.63
     regenerate
    0.63
     forgiven
    0.62
    justified
    0.59
     pardoned
    0.59
     justific
    0.55
    Activations Density 1.080%

    No Known Activations