© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13108
    Prev
    Next
    INDEX
    Explanations

    sentences describing religious worship and spaces, particularly in reference to God or Allah.

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    RegressionTest
    -0.83
    MigrationBuilder
    -0.77
    InvalidProtocol
    -0.72
    ConstraintMaker
    -0.69
    IUrlHelper
    -0.65
     StringTokenizer
    -0.64
    ooplankton
    -0.56
    NamedQuery
    -0.54
    enumi
    -0.54
     vuitton
    -0.54
    POSITIVE LOGITS
    tvguidetime
    0.61
     Samaria
    0.54
    MemoryWarning
    0.52
     ***!
    0.52
    CPtr
    0.49
     Jop
    0.47
    sacrific
    0.47
    
    0.45
    водство
    0.45
     nodeId
    0.42
    Activations Density 6.737%

    No Known Activations