© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16092
    Prev
    Next
    INDEX
    Explanations

    discussion of opportunities or other advantages in a given situation

    oai_token-act-pair · gemini-2.0-flash

    opportunity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Monfieur
    -1.16
     myſelf
    -1.11
     itſelf
    -1.09
     Efq
    -1.06
     Shakspeare
    -1.06
     fubject
    -0.96
     Chriftian
    -0.96
     Baillargeon
    -0.96
     crdi
    -0.96
     Jefus
    -0.95
    POSITIVE LOGITS
     for
    0.65
     at
    0.63
     to
    0.59
     au
    0.56
     "
    0.50
     taken
    0.50
     ra
    0.48
     of
    0.48
     us
    0.47
    <eos>
    0.47
    Activations Density 4.791%

    No Known Activations