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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15107
    Prev
    Next
    INDEX
    Explanations

    the word "newly" and sometimes numbers near it

    oai_token-act-pair · gemini-2.0-flash

    newly

    np_max-act · gemini-2.0-flash

    ▁newly

    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
    ^(@)
    -2.41
     Efq
    -2.30
     myſelf
    -2.23
     Jefus
    -2.22
     itſelf
    -2.17
    ſelf
    -2.13
     Theſe
    -2.09
    ſelves
    -2.03
     $_"
    -2.03
     themſelves
    -2.02
    POSITIVE LOGITS
    ↵↵
    1.57
    1
    1.29
    ↵
    1.27
     
    1.26
    .
    1.25
    <strong>
    1.20
    2
    1.19
    <eos>
    1.18
      
    1.15
    <em>
    1.11
    Activations Density 1.214%

    No Known Activations