© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2821
    Prev
    Next
    INDEX
    Explanations

    the letters "th" in various contexts, sometimes within URLs, code snippets, or general text

    oai_token-act-pair · gemini-2.0-flash

    code/URLs

    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
     Reach
    -0.71
    reached
    -0.68
    RepeatedField
    -0.66
    reach
    -0.65
     REACH
    -0.63
     reach
    -0.61
     reaches
    -0.60
     reaching
    -0.58
    Reach
    -0.58
    يميديا
    -0.57
    POSITIVE LOGITS
    op
    0.61
    
    0.55
     MainAxisSize
    0.54
    OP
    0.51
     BorderRadius
    0.50
    obal
    0.49
    MigrationBuilder
    0.48
    ob
    0.48
     propTypes
    0.47
    setOpaque
    0.46
    Activations Density 0.710%

    No Known Activations