© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6866
    Prev
    Next
    INDEX
    Explanations

    language related to Christianity

    oai_token-act-pair · gemini-2.0-flash

    religious concepts

    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
    يكب
    -0.62
     Mémoires
    -0.54
     alkaloids
    -0.53
     Arxivat
    -0.53
     Reſ
    -0.53
     Monfieur
    -0.52
     houſe
    -0.52
     Dietz
    -0.51
     通販
    -0.51
     kawasaki
    -0.50
    POSITIVE LOGITS
    }}/>
    0.50
    awtextra
    0.50
    endorff
    0.49
    렇
    0.49
    гну
    0.49
    AddHtmlAttribute
    0.49
    ništ
    0.49
    gantung
    0.48
    Introduced
    0.47
    teni
    0.47
    Activations Density 11.010%

    No Known Activations