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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3099
    Prev
    Next
    INDEX
    Explanations

    phrases generally related to Christianity, including belief, relationship, and worship.

    oai_token-act-pair · gemini-2.0-flash

    religious terms and references

    np_token-act-pair-logits · gpt-4o-mini

    Christianity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     informée
    -0.58
    กัด
    -0.52
    tracks
    -0.46
    ynki
    -0.46
    曲目
    -0.42
     квітня
    -0.41
     pregi
    -0.41
     Wikimedijinoj
    -0.41
    Motion
    -0.41
    Décès
    -0.40
    POSITIVE LOGITS
    MemoryWarning
    0.82
    RegressionTest
    0.69
     God
    0.68
     Jesus
    0.66
     referenties
    0.65
     Chriſt
    0.63
    #+#
    0.62
     Jefus
    0.61
    SequentialGroup
    0.61
    Jesus
    0.61
    Activations Density 3.673%

    No Known Activations