© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11340
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs used to form compound tenses

    oai_token-act-pair · gemini-2.0-flash

    Verb "to have"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    astify
    -0.63
     artikkelen
    -0.59
    ณ์
    -0.59
     associative
    -0.58
     Seeder
    -0.56
    ModelSerializer
    -0.56
    STRICT
    -0.55
    ariste
    -0.55
    عيد
    -0.55
    painter
    -0.55
    POSITIVE LOGITS
     تضيفلها
    0.59
    AndEndTag
    0.57
    <bos>
    0.57
     currently
    0.55
    ']))
    0.53
     hiện
    0.52
     progre
    0.51
     nakalista
    0.51
    avía
    0.50
     has
    0.48
    Activations Density 0.804%

    No Known Activations