© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8673
    Prev
    Next
    INDEX
    Explanations

    code related to caching

    oai_token-act-pair · gemini-2.0-flash

    computer cache

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     underground
    -2.08
     Underground
    -1.90
    Underground
    -1.84
    underground
    -1.82
     Cache
    -1.72
     cache
    -1.69
     CACHE
    -1.61
    cache
    -1.59
     cached
    -1.59
     subterranean
    -1.58
    POSITIVE LOGITS
     Trenton
    0.50
    aryen
    0.50
     Fior
    0.48
     Krim
    0.47
     Liss
    0.47
     phẩm
    0.47
    olunt
    0.46
     Lisboa
    0.45
    ValueGenerated
    0.45
    NSURL
    0.44
    Activations Density 2.340%

    No Known Activations