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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7100
    Prev
    Next
    INDEX
    Explanations

    citations or references

    oai_token-act-pair · gemini-2.0-flash

    Foreign language words

    np_max-act-logits · gemini-2.0-flash

    say "capitalized names"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     ❖
    -0.42
     
    -0.40
     ◦
    -0.39
     
    -0.38
     
    -0.38
     ▼
    -0.38
     ➢
    -0.37
     \(
    -0.37
    ​.
    -0.37
     (+)
    -0.37
    POSITIVE LOGITS
     enfans
    0.72
     feroit
    0.68
     avoient
    0.67
     auroit
    0.65
     Grecs
    0.63
     chré
    0.62
     noires
    0.61
     étoient
    0.60
     pouvoit
    0.59
     démocr
    0.59
    Activations Density 9.796%

    No Known Activations