© 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. 6608
    Prev
    Next
    INDEX
    Explanations

    passages about conflict, oppression and political action

    oai_token-act-pair · gemini-2.0-flash

    terms related to societal control and exploitation

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

    Seizing power and resources

    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
     nahilalakip
    -0.74
    GraphicsUnit
    -0.74
     AssemblyCulture
    -0.72
    updateOne
    -0.64
    @[+][
    -0.63
    ponses
    -0.62
     MainAxisSize
    -0.62
    Tembelea
    -0.61
    XmlAccessorType
    -0.60
    miyorum
    -0.60
    POSITIVE LOGITS
    TagMode
    0.62
     schools
    0.47
     cemeteries
    0.46
     wealth
    0.44
     transférez
    0.43
    RTLR
    0.43
     걸
    0.41
     services
    0.41
     jobs
    0.41
     resources
    0.41
    Activations Density 4.244%

    No Known Activations