© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11901
    Prev
    Next
    INDEX
    Explanations

    tokens that are frequently used when talking about chemistry

    oai_token-act-pair · gemini-2.0-flash

    terms related to bedrooms

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

    bedroom

    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
     IFTT
    -0.61
    捞
    -0.57
     AssemblyTitle
    -0.56
    qwerty
    -0.54
     useAppContext
    -0.54
    ArrowToggle
    -0.53
     Efe
    -0.52
     Myron
    -0.51
    tableFuture
    -0.50
    fir
    -0.50
    POSITIVE LOGITS
     bedrooms
    0.84
     bedroom
    0.84
     bed
    0.77
     Bed
    0.74
     Bedroom
    0.73
    bedroom
    0.72
     Bedrooms
    0.69
    Bed
    0.68
    BED
    0.68
     BEDROOM
    0.67
    Activations Density 2.988%

    No Known Activations