© 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. 4620
    Prev
    Next
    INDEX
    Explanations

    words related to cause and effect as well as words related to problem solving

    oai_token-act-pair · gemini-2.0-flash

    cause

    np_max-act · gemini-2.0-flash
    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
     ligiloj
    -0.90
    Portail
    -0.87
    DeleteBehavior
    -0.76
    Boas
    -0.74
    WebVitals
    -0.74
    外部リンク
    -0.73
    StoryboardSegue
    -0.72
    djangoproject
    -0.71
    Portale
    -0.69
     referrerpolicy
    -0.69
    POSITIVE LOGITS
    <bos>
    0.70
    ↵↵
    0.61
    utiliser
    0.54
    клопе
    0.54
     exchanging
    0.52
     communicating
    0.52
     manipulating
    0.51
     contacted
    0.50
    nitten
    0.50
     detecting
    0.49
    Activations Density 1.494%

    No Known Activations