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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6338
    Prev
    Next
    INDEX
    Explanations

    the prefix "non-"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "non"

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

    non

    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
    tabilidade
    -0.43
    vocato
    -0.42
    Compilation
    -0.41
     Bài
    -0.40
    σκευ
    -0.40
    liminary
    -0.40
    losigkeit
    -0.40
     estuviera
    -0.40
    FINE
    -0.40
     Nature
    -0.40
    POSITIVE LOGITS
     Reverso
    0.62
    Vidite
    0.61
    queryInterface
    0.60
    
    0.55
    NamedQueries
    0.54
     nonUne
    0.54
     transfieras
    0.51
     الرياضيه
    0.50
     meaning
    0.48
     հղումներ
    0.48
    Activations Density 0.630%

    No Known Activations