© 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. 8514
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and derivatives

    oai_token-act-pair · gemini-2.0-flash

    variables

    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
     Shakspeare
    -0.93
     Cæsar
    -0.87
     avoient
    -0.81
     panoramique
    -0.80
     moschino
    -0.80
    StoryboardSegue
    -0.79
     auroit
    -0.79
     romantique
    -0.77
     chré
    -0.76
     étoient
    -0.76
    POSITIVE LOGITS
     X
    0.60
     x
    0.55
     J
    0.55
     A
    0.54
     α
    0.53
     â
    0.52
     U
    0.50
     Q
    0.50
    ².
    0.50
     dé
    0.50
    Activations Density 7.361%

    No Known Activations