© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11703
    Prev
    Next
    INDEX
    Explanations

    financial transactions, percentages, ownership, or agreements

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to navigation and UI elements

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

    business and finance

    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
    tagHelperRunner
    -0.69
    InputBorder
    -0.68
    enderror
    -0.66
    UserScript
    -0.64
    Personendaten
    -0.62
    Carrière
    -0.60
     Pompey
    -0.59
     كومونز
    -0.58
     Mugh
    -0.58
     OFDb
    -0.58
    POSITIVE LOGITS
    StackNavigator
    0.46
    ViewById
    0.43
     mi
    0.42
     pasti
    0.41
     Betts
    0.41
    PADDING
    0.41
     holding
    0.40
    rlrl
    0.40
     Southwest
    0.40
    Click
    0.40
    Activations Density 2.575%

    No Known Activations