© 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. 7861
    Prev
    Next
    INDEX
    Explanations

    code snippets including things like curly braces, colors, and styles

    oai_token-act-pair · gemini-2.0-flash

    CSS styling

    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
    processable
    -0.61
    ubere
    -0.58
     Pacheco
    -0.56
    nerf
    -0.56
    fortable
    -0.56
    undas
    -0.56
    acked
    -0.56
    ARROLL
    -0.56
    ustimmung
    -0.56
     operands
    -0.54
    POSITIVE LOGITS
    marginRight
    0.60
    marginLeft
    0.60
    paddingVertical
    0.58
     betweenstory
    0.57
    borderRadius
    0.56
    marginVertical
    0.56
    paddingRight
    0.54
    paddingTop
    0.52
     marginLeft
    0.52
    GOTREF
    0.50
    Activations Density 0.501%

    No Known Activations