© 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. 1098
    Prev
    Next
    INDEX
    Explanations

    words that sound positive about growth and understanding

    oai_token-act-pair · gemini-2.0-flash

    improvements and increases

    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
     nahilalakip
    -0.50
    cipais
    -0.47
    Hochspringen
    -0.44
    setModal
    -0.44
    bera
    -0.43
    født
    -0.42
    WireFormatLite
    -0.42
     oprot
    -0.41
     distanciation
    -0.41
    isait
    -0.41
    POSITIVE LOGITS
    europa
    0.65
    ContentAlignment
    0.58
    AsUp
    0.57
    membership
    0.56
    collapsed
    0.55
    CMOS
    0.54
    )))));
    0.54
     Failures
    0.54
     opérateur
    0.54
    Fizz
    0.52
    Activations Density 2.286%

    No Known Activations