© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8570
    Prev
    Next
    INDEX
    Explanations

    phrases that put things into context.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -1.69
    contentLoaded
    -0.65
    ChildScrollView
    -0.64
     <<<<<<<<<<<<<<
    -0.64
    PyExc
    -0.63
    styleType
    -0.63
    ModelSerializer
    -0.62
    Descripció
    -0.60
    .*")]
    -0.59
     للمعارف
    -0.55
    POSITIVE LOGITS
     traduire
    0.50
     connection
    0.49
    ]--;
    0.48
     trace
    0.48
     uman
    0.47
    autoload
    0.46
    oprene
    0.46
    ldg
    0.45
     veřej
    0.45
    ילת
    0.45
    Activations Density 3.655%

    No Known Activations