© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9698
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers

    oai_token-act-pair · gemini-2.0-flash

    say "0"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    setVerticalGroup
    -0.62
    المناصب
    -0.62
     الدولى
    -0.53
     ten
    -0.52
     propOrder
    -0.51
    kari
    -0.49
    heon
    -0.49
    όμε
    -0.48
    WriteBarrier
    -0.47
    erus
    -0.47
    POSITIVE LOGITS
     opérateur
    0.50
    +:+
    0.50
    IsContent
    0.50
    <bos>
    0.49
     ImportError
    0.48
    crollView
    0.47
     Roskov
    0.47
    quoi
    0.46
     Biôgrafia
    0.46
    createServer
    0.46
    Activations Density 3.173%

    No Known Activations