© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10289
    Prev
    Next
    INDEX
    Explanations

    phrases discussing a couple reducing their public presence

    oai_token-act-pair · gemini-2.0-flash

    variants of the word 'low'

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

    low, whispered

    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
    pernicus
    -0.45
    AddHtmlAttribute
    -0.41
    haq
    -0.36
    itan
    -0.36
    mismo
    -0.36
    rations
    -0.36
    柯
    -0.36
     Snowflake
    -0.35
    MockBean
    -0.34
     என்று
    -0.34
    POSITIVE LOGITS
     low
    1.83
    low
    1.55
    Low
    1.53
     Low
    1.52
     LOW
    1.43
    LOW
    1.33
     lowest
    1.17
    低
    1.17
     soft
    1.13
     rendah
    1.06
    Activations Density 1.392%

    No Known Activations