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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 897
    Prev
    Next
    INDEX
    Explanations

    words describing needing and desire

    oai_token-act-pair · gemini-2.0-flash

    need

    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
    ſelf
    -0.66
     necesitaba
    -0.64
    ThroughAttribute
    -0.63
    Needs
    -0.63
     itſelf
    -0.62
     necesitamos
    -0.61
    RetentionPolicy
    -0.61
    needs
    -0.61
     himſelf
    -0.60
    SequentialGroup
    -0.59
    POSITIVE LOGITS
     CreateTagHelper
    0.59
    árl
    0.56
    yto
    0.50
    赶
    0.48
    ueuse
    0.48
    äure
    0.47
    ICIAS
    0.47
     fond
    0.46
    romyalgia
    0.46
    χε
    0.46
    Activations Density 16.379%

    No Known Activations