© 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. 3499
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific studies and research

    oai_token-act-pair · gemini-2.0-flash

    words indicating necessity or requirement

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

    verb "to 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
     needed
    -1.42
     need
    -1.38
     require
    -1.29
    needed
    -1.28
     needs
    -1.28
     Need
    -1.25
     Needs
    -1.23
     Needed
    -1.23
    Need
    -1.21
     required
    -1.20
    POSITIVE LOGITS
     is
    0.94
     are
    0.54
     adalah
    0.51
     là
    0.46
     seria
    0.46
    是
    0.44
     jsou
    0.44
     것이
    0.43
     Is
    0.43
     é
    0.43
    Activations Density 1.594%

    No Known Activations