© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11933
    Prev
    Next
    INDEX
    Explanations

    words related to projects, planning, changes, documents and studies

    oai_token-act-pair · gemini-2.0-flash

    are were

    np_max-act-logits · gemini-2.0-flash

    plural nouns (ending -s)

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     is
    -0.57
    Has
    -0.56
     Has
    -0.53
     was
    -0.50
    has
    -0.50
     Was
    -0.49
    Was
    -0.49
    fortawesome
    -0.48
    Knows
    -0.47
    was
    -0.47
    POSITIVE LOGITS
     are
    2.08
     were
    1.67
     aren
    1.45
     weren
    1.33
     ARE
    1.28
     arent
    1.23
     sont
    1.21
    are
    1.20
    were
    1.20
     são
    1.14
    Activations Density 4.264%

    No Known Activations