© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12483
    Prev
    Next
    INDEX
    Explanations

    words about difficult or trying situations

    oai_token-act-pair · gemini-2.0-flash

    tests and trials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     acrylique
    -0.52
     дописавши
    -0.52
    今日も
    -0.51
    faker
    -0.51
     (;;
    -0.50
    tyg
    -0.48
     старости
    -0.47
     numériques
    -0.47
     plagio
    -0.47
     gobier
    -0.46
    POSITIVE LOGITS
    ]")]
    0.66
     testing
    0.63
    épreuve
    0.58
     awakeFromNib
    0.58
     Testing
    0.56
    மைய
    0.55
     thử
    0.55
    testing
    0.54
     challenges
    0.54
     tested
    0.54
    Activations Density 0.388%

    No Known Activations