© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5404
    Prev
    Next
    INDEX
    Explanations

    occurrences of the words "you", "I", "if", "so", "when", "but", "please", and ", and", especially when adjacent to commas

    oai_token-act-pair · gemini-2.0-flash

    verbs suggesting actions or choices

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

    Suggesting actions

    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
     ddelweddau
    -0.49
     utafitiHapana
    -0.48
     păr
    -0.42
     fazendo
    -0.41
     facendo
    -0.41
    contentLoaded
    -0.41
     haciendo
    -0.40
     recibiendo
    -0.40
    astéroïdes
    -0.39
    Not
    -0.39
    POSITIVE LOGITS
     consider
    0.99
     try
    0.96
     choose
    0.87
     prepare
    0.87
     visit
    0.87
     use
    0.86
     decide
    0.84
     watch
    0.84
     create
    0.83
     check
    0.82
    Activations Density 2.230%

    No Known Activations