© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14152
    Prev
    Next
    INDEX
    Explanations

    the word "the" preceded or followed by certain other words.

    oai_token-act-pair · gemini-2.0-flash

    industries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     الذات
    -0.40
     kolejny
    -0.39
     cesse
    -0.39
     parche
    -0.38
     comerciales
    -0.37
    idopsis
    -0.36
     commerciale
    -0.36
    rtx
    -0.36
    :+:
    -0.36
    了自己的
    -0.36
    POSITIVE LOGITS
     nakalista
    1.02
    TagMode
    0.89
    Personendaten
    0.87
     propOrder
    0.82
     referrerpolicy
    0.77
    ngdoc
    0.77
    ArgumentParser
    0.76
     EconPapers
    0.75
    AnchorStyles
    0.74
     HasFactory
    0.73
    Activations Density 3.771%

    No Known Activations