© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8123
    Prev
    Next
    INDEX
    Explanations

    words or phrases in scientific literature

    oai_token-act-pair · gemini-2.0-flash

    past tense verbs

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

    scientific data

    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
     always
    -0.50
     also
    -0.48
    .
    -0.47
     still
    -0.46
     probably
    -0.45
     already
    -0.45
     
    -0.45
    do
    -0.44
    出一
    -0.44
    when
    -0.43
    POSITIVE LOGITS
     was
    1.11
     furent
    0.96
     were
    0.96
    MLLoader
    0.95
     تانيه
    0.78
    躇
    0.77
    Autoritní
    0.77
     wasn
    0.76
     furono
    0.76
    Was
    0.75
    Activations Density 4.210%

    No Known Activations