© 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. 1924
    Prev
    Next
    INDEX
    Explanations

    the prefix "pla," especially when followed by related letters

    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
     surla
    -0.77
     Cæsar
    -0.69
     disambiguazione
    -0.65
    SupportActionBar
    -0.64
     ſhe
    -0.63
    BorderFactory
    -0.62
     ſtate
    -0.61
     ftate
    -0.61
     Formosa
    -0.60
     onData
    -0.59
    POSITIVE LOGITS
     Gut
    0.52
    iner
    0.51
    akan
    0.50
     S
    0.50
    nant
    0.49
     Dis
    0.47
    zati
    0.44
     Par
    0.44
    ics
    0.44
    dis
    0.44
    Activations Density 0.848%

    No Known Activations