© 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. 319
    Prev
    Next
    INDEX
    Explanations

    words relating to academic research and knowledge transfer

    oai_token-act-pair · gemini-2.0-flash

    Social science texts

    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
    AndEndTag
    -1.06
    DockStyle
    -0.91
     kasarigan
    -0.89
     AssemblyCulture
    -0.82
     مشين
    -0.79
    setVerticalGroup
    -0.79
    TintMode
    -0.79
    protoimpl
    -0.74
    NewUrlParser
    -0.73
    EDEFAULT
    -0.72
    POSITIVE LOGITS
    acchi
    0.48
     co
    0.47
     charset
    0.47
     obstet
    0.44
     Vikipedi
    0.44
    ouro
    0.44
    CodeAttribute
    0.42
     extruded
    0.41
    oper
    0.41
    oria
    0.41
    Activations Density 10.772%

    No Known Activations