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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5793
    Prev
    Next
    INDEX
    Explanations

    negative experiences, often described as burdens

    oai_token-act-pair · gemini-2.0-flash

    concepts related to burden or weight

    np_token-act-pair-logits · gpt-4o-mini

    burden

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    -0.73
     تضيفلها
    -0.60
    WireFormatLite
    -0.56
    philis
    -0.56
     ब्रेकडाउन
    -0.55
    PerformLayout
    -0.53
     autorytatywna
    -0.52
     ComVisible
    -0.52
    hyrchwyd
    -0.52
    Réalisation
    -0.52
    POSITIVE LOGITS
     heavy
    1.21
     heaviest
    1.20
     weight
    1.13
    heavy
    1.11
     Heavy
    1.11
     heavier
    1.09
     weights
    1.08
     HEAVY
    1.08
    Heavy
    1.05
     carrying
    1.05
    Activations Density 2.577%

    No Known Activations