© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 103
    Prev
    Next
    INDEX
    Explanations

    terms related to religion, faith, and commitment

    oai_token-act-pair · gemini-2.0-flash

    God

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    >[]
    -0.61
    SourceChecksum
    -0.60
    __]
    -0.53
    yethylene
    -0.51
    rfloor
    -0.50
     nakalista
    -0.49
    ValueStyle
    -0.49
    RTSC
    -0.49
     AssemblyProduct
    -0.48
    YMMV
    -0.48
    POSITIVE LOGITS
    PickerController
    0.58
    posedge
    0.57
     occaf
    0.57
     purpoſe
    0.57
     secondaires
    0.54
     Anſ
    0.52
    WebVitals
    0.51
     Monfieur
    0.50
    itename
    0.50
     raiſ
    0.49
    Activations Density 1.294%

    No Known Activations