© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 66
    Prev
    Next
    INDEX
    Explanations

    technical explanations or descriptions, as well as references to children's activities.

    oai_token-act-pair · gemini-2.0-flash

    research and experiments

    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
    IsContent
    -0.65
    IContainer
    -0.51
     ph
    -0.43
    charCodeAt
    -0.40
     אות
    -0.39
    لينكات
    -0.38
    stdc
    -0.38
     incorporated
    -0.37
    </caption>
    -0.37
    $_.
    -0.37
    POSITIVE LOGITS
     disponibilités
    0.79
    ThroughAttribute
    0.77
     متعلقه
    0.75
     surla
    0.73
    expandindo
    0.69
    complexContent
    0.68
    WithIOException
    0.65
     насељу
    0.63
    inguished
    0.63
     <=",
    0.63
    Activations Density 6.517%

    No Known Activations