© 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. 4901
    Prev
    Next
    INDEX
    Explanations

    sentences which use a passive voice.

    oai_token-act-pair · gemini-2.0-flash

    terms related to recommendations and considerations

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

    be

    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
     Theſe
    -0.63
     Shakspeare
    -0.60
    toMatchSnapshot
    -0.57
     BoxDecoration
    -0.57
    viewWillAppear
    -0.56
     houſe
    -0.54
     ſeveral
    -0.54
    ChildScrollView
    -0.54
     برانيه
    -0.53
     becauſe
    -0.53
    POSITIVE LOGITS
     addressed
    0.79
     address
    0.69
    addressed
    0.66
     AssemblyCulture
    0.66
     explored
    0.65
     Paglinawan
    0.65
     discussed
    0.63
     responded
    0.61
     tackled
    0.59
    address
    0.59
    Activations Density 2.835%

    No Known Activations