© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3084
    Prev
    Next
    INDEX
    Explanations

    numerical values preceded by line breaks

    oai_token-act-pair · gemini-2.0-flash

    factual snippets

    np_max-act · gemini-2.0-flash

    ▁

    np_max-act-logits · gpt-5-mini
    Triggered 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
    Negative Logits
     
    -5.00
    ↵↵
    -3.14
     (
    -2.97
      
    -2.88
    ↵
    -2.75
    <eos>
    -2.58
     I
    -2.55
     A
    -2.50
     a
    -2.44
     the
    -2.42
    POSITIVE LOGITS
     Efq
    5.56
     myſelf
    5.47
     Monfieur
    5.22
     itſelf
    5.19
     Theſe
    4.88
     Anſ
    4.84
     Majefty
    4.84
     Jefus
    4.84
     ―――――
    4.81
     Houſe
    4.78
    Activations Density 2.480%

    No Known Activations