© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6087
    Prev
    Next
    INDEX
    Explanations

    mentions of performers or artists, and sometimes "man."

    oai_token-act-pair · gemini-2.0-flash

    artists

    np_max-act · gemini-2.0-flash

    artists

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     myſelf
    -1.63
     auffi
    -1.53
     purpoſe
    -1.52
     Theſe
    -1.48
     raiſ
    -1.45
     itſelf
    -1.45
     leaſt
    -1.44
     uſe
    -1.43
     ſhe
    -1.42
     whoſe
    -1.42
    POSITIVE LOGITS
     
    1.38
    ↵↵
    1.12
     The
    1.00
     -
    1.00
     A
    0.95
     in
    0.94
     He
    0.92
     (
    0.91
     N
    0.90
     D
    0.89
    Activations Density 1.553%

    No Known Activations