© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9779
    Prev
    Next
    INDEX
    Explanations

    filler words and phrases used in common conversation

    oai_token-act-pair · gemini-2.0-flash

    temporal prepositions

    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
     Kind
    -0.79
     Know
    -0.74
     Value
    -0.74
     Feel
    -0.73
    Know
    -0.73
    Styleable
    -0.71
     Nice
    -0.71
    Ótimo
    -0.69
    Define
    -0.68
    "]="
    -0.68
    POSITIVE LOGITS
     After
    1.01
     During
    1.00
    After
    0.95
     Over
    0.94
    During
    0.94
     Before
    0.89
     Through
    0.88
     Later
    0.88
     Following
    0.88
    Over
    0.85
    Activations Density 39.545%

    No Known Activations