Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 2109
    Prev
    Next
    INDEX
    Explanations

    sentences containing auxiliary verbs with other verbs that indicate the state of something

    oai_token-act-pair · gemini-2.0-flash

    followed

    np_max-act-logits · gemini-2.0-flash
    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
     followed
    -1.09
     accompanied
    -0.99
     Followed
    -0.91
    followed
    -0.90
     complemented
    -0.90
     preceded
    -0.89
     replaced
    -0.88
     assisted
    -0.82
    Followed
    -0.80
     supplemented
    -0.76
    POSITIVE LOGITS
     werd
    0.60
     été
    0.59
     was
    0.57
     essere
    0.57
     được
    0.57
     être
    0.56
     být
    0.55
     została
    0.54
     бути
    0.51
     beginnetje
    0.51
    Activations Density 1.890%

    No Known Activations