© 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. 4607
    Prev
    Next
    INDEX
    Explanations

    the phrase "and so on"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "so"

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

    so

    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
    
    -0.92
     nakalista
    -0.75
    oredCriteria
    -0.75
     Paglinawan
    -0.75
    ⤹
    -0.73
     beginnetje
    -0.71
     Waray
    -0.71
    ьаж
    -0.71
    IsMutable
    -0.69
    MLLoader
    -0.69
    POSITIVE LOGITS
     on
    0.62
    yente
    0.46
     mères
    0.45
     relazioni
    0.42
     chrétiens
    0.41
     pomoci
    0.41
     pareti
    0.41
     scatola
    0.40
     privés
    0.40
     vectoriales
    0.40
    Activations Density 0.943%

    No Known Activations