© 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. 9602
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases with several references to the same topic

    oai_token-act-pair · 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
     enough
    -3.20
    enough
    -2.94
     Enough
    -2.77
    Enough
    -2.64
     ENOUGH
    -2.61
     genug
    -2.31
     genoeg
    -2.09
     suficiente
    -1.93
     sufficient
    -1.80
     suficientes
    -1.79
    POSITIVE LOGITS
     fast
    0.53
    ellus
    0.45
    muş
    0.44
    fast
    0.43
    porus
    0.42
    rensen
    0.42
    devtool
    0.42
    jonijiet
    0.41
     hard
    0.41
     Vasco
    0.41
    Activations Density 5.978%

    No Known Activations