Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 7091
    Prev
    Next
    INDEX
    Explanations

    words related to the future and the concept of long-term benefit and decision making

    oai_token-act-pair · gemini-2.0-flash

    planning and choices

    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
    AndEndTag
    -0.56
    createStatement
    -0.50
     priser
    -0.49
    isContained
    -0.49
    UseVisualStyle
    -0.45
    uração
    -0.44
     tombé
    -0.43
    featureID
    -0.41
    wpdb
    -0.41
     moda
    -0.41
    POSITIVE LOGITS
     Paglinawan
    0.71
    Personendaten
    0.69
    BibitemShut
    0.69
     متعلقه
    0.68
    ukunft
    0.68
     IndexPath
    0.68
    ThroughAttribute
    0.67
     Meksiku
    0.67
    UpInside
    0.64
     linkovi
    0.61
    Activations Density 1.247%

    No Known Activations