© 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. 8704
    Prev
    Next
    INDEX
    Explanations

    passages discussing programming, code efficiency, simplicity, functions, and visibility of names

    oai_token-act-pair · gemini-2.0-flash

    Code efficiency and comparisons

    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
    CURLOPT
    -0.65
     CURLOPT
    -0.47
    wl
    -0.42
     surla
    -0.42
    роди
    -0.40
    asi
    -0.38
    TagHelper
    -0.37
    itato
    -0.37
    enza
    -0.37
    脚注の使い方
    -0.37
    POSITIVE LOGITS
     Efq
    1.08
     faſt
    1.05
     Monfieur
    1.02
     pleaſure
    0.97
     ſta
    0.95
     myſelf
    0.93
     Reſ
    0.92
     iſt
    0.91
     houſe
    0.88
     ſmall
    0.88
    Activations Density 5.375%

    No Known Activations