© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8186
    Prev
    Next
    INDEX
    Explanations

    the first four letters of the word "shop" or "shoe"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    strconv
    -0.64
    IANGLES
    -0.60
    AsUp
    -0.59
    antMatchers
    -0.59
    dónde
    -0.57
    Gemeinden
    -0.57
     चीज़ों
    -0.57
     Terence
    -0.56
    PushMatrix
    -0.56
    ManyToOne
    -0.55
    POSITIVE LOGITS
     تانيه
    0.61
     Himo
    0.48
    ale
    0.47
    +:+
    0.46
     carriera
    0.46
    ckey
    0.45
     للاسماء
    0.43
    存于互联网档案馆
    0.41
     icône
    0.41
     lemn
    0.41
    Activations Density 1.007%

    No Known Activations