© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6194
    Prev
    Next
    INDEX
    Explanations

    words or phrases that describe relationships or connections

    oai_token-act-pair · gemini-2.0-flash

    words related to associations and connections

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

    associated

    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
     connected
    -0.83
     connection
    -0.82
     linked
    -0.77
     Connected
    -0.76
     associated
    -0.75
     tied
    -0.70
     Connection
    -0.66
    connected
    -0.65
     association
    -0.65
     related
    -0.64
    POSITIVE LOGITS
     propOrder
    0.60
    ))^
    0.52
    mailto
    0.51
    serviceWorker
    0.50
    Código
    0.48
    帖最后由
    0.48
     صوتيه
    0.47
    umbar
    0.47
    rspec
    0.47
     with
    0.47
    Activations Density 5.803%

    No Known Activations