© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3461
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express strong emotional reactions

    oai_token-act-pair · gemini-2.0-flash

    stress/strong emotion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     itſelf
    -1.06
     myſelf
    -1.05
    ſelf
    -0.97
     Diſ
    -0.96
     themſelves
    -0.91
     Jefus
    -0.91
     ―――――
    -0.90
     iſt
    -0.90
     Reſ
    -0.88
     ſy
    -0.88
    POSITIVE LOGITS
     P
    0.52
     O
    0.49
     
    0.45
     G
    0.45
     K
    0.43
     po
    0.43
    vocable
    0.43
     E
    0.43
     or
    0.42
    <eos>
    0.42
    Activations Density 55.994%

    No Known Activations