© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5415
    Prev
    Next
    INDEX
    Explanations

    mentions of numbered districts, passages, or judicial circuits

    oai_token-act-pair · gemini-2.0-flash

    technical terms or database terms

    np_token-act-pair-logits · gpt-4o-mini

    dates and ordinals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     fifth
    -1.91
     sixth
    -1.89
     fourth
    -1.87
     third
    -1.87
     seventh
    -1.81
     ninth
    -1.78
     eighth
    -1.73
     tenth
    -1.73
    third
    -1.66
     twelfth
    -1.65
    POSITIVE LOGITS
    Personendaten
    0.60
    AccessorTable
    0.51
    newswire
    0.45
    Diweddarwch
    0.43
     Infórmanos
    0.42
    autorest
    0.42
    NewRow
    0.42
    SerializedName
    0.41
     فريبيس
    0.40
    MethodManager
    0.40
    Activations Density 1.252%

    No Known Activations