© 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. 8058
    Prev
    Next
    INDEX
    Explanations

    religious texts referring to God or gods

    oai_token-act-pair · gemini-2.0-flash

    terms related to worship or religious references

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

    Islamic terms

    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
    RenderAtEndOf
    -0.69
    RegressionTest
    -0.61
    GraphicsUnit
    -0.58
    tagext
    -0.57
    TypedDataSet
    -0.51
     BoxFit
    -0.50
    UseVisualStyle
    -0.50
     OMITBAD
    -0.49
    UpInside
    -0.48
     useRouter
    -0.46
    POSITIVE LOGITS
     mosque
    0.64
     Walkover
    0.63
     mosques
    0.62
    IBar
    0.59
     Mohamed
    0.58
     шей
    0.57
    prop
    0.56
     Ahmad
    0.55
    PROP
    0.54
    Източници
    0.54
    Activations Density 6.444%

    No Known Activations