© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6662
    Prev
    Next
    INDEX
    Explanations

    dates and numbers, especially monetary figures and quantities, but also identifiers like patent numbers.

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    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
     propOrder
    -0.54
     WRIGHT
    -0.51
     strtok
    -0.47
    velopes
    -0.47
     cheered
    -0.43
    viewWillAppear
    -0.43
     strolled
    -0.43
    嘘
    -0.43
     alligator
    -0.43
     '\''
    -0.43
    POSITIVE LOGITS
     ETS
    0.56
     MEC
    0.54
    EOT
    0.54
     Mf
    0.54
     MW
    0.54
     BPS
    0.54
     TSC
    0.53
     Mts
    0.53
    TRIBUN
    0.53
     PW
    0.52
    Activations Density 33.955%

    No Known Activations