© 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. 12815
    Prev
    Next
    INDEX
    Explanations

    references to discovering one's life calling or purpose.

    oai_token-act-pair · gemini-2.0-flash

    passion and purpose

    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
     تانيه
    -0.57
    辞典
    -0.49
    <bos>
    -0.47
    ::_('
    -0.47
     device
    -0.47
    los
    -0.43
     kind
    -0.42
    VersionUID
    -0.41
    enumi
    -0.40
    百
    -0.40
    POSITIVE LOGITS
     propOrder
    0.85
     Biôgrafia
    0.77
    fjspx
    0.76
    ContentAsync
    0.74
     saites
    0.73
     kasarigan
    0.72
     betweenstory
    0.71
    AddTagHelper
    0.71
     gyhoeddwyd
    0.69
     Roskov
    0.68
    Activations Density 0.754%

    No Known Activations