© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8496
    Prev
    Next
    INDEX
    Explanations

    code snippets and questions including the keyword "delete"

    oai_token-act-pair · gemini-2.0-flash

    de

    np_max-act · gemini-2.0-flash

    ▁de

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     estekak
    -0.69
    sonaro
    -0.63
    <bos>
    -0.63
     OnInit
    -0.57
     <=",
    -0.56
    InitVars
    -0.55
    )":
    -0.54
    
    -0.53
    '".
    -0.53
    preventDefault
    -0.53
    POSITIVE LOGITS
     Deel
    0.63
    Datuak
    0.63
     näin
    0.61
     للاسماء
    0.60
    СТВ
    0.54
     ekster
    0.52
    voorbeeld
    0.51
     Barnabas
    0.50
     Kategor
    0.50
    valis
    0.50
    Activations Density 1.098%

    No Known Activations