Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 979
    Prev
    Next
    INDEX
    Explanations

    words or characters associated with units, ratios, percentages, cost, or measurement

    oai_token-act-pair · gemini-2.0-flash

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    titleMargin
    -0.77
     per
    -0.67
     Per
    -0.59
     Италијани
    -0.59
    adget
    -0.55
    }}_{\
    -0.55
    per
    -0.54
    }`).
    -0.54
    ooplankton
    -0.54
    Per
    -0.53
    POSITIVE LOGITS
     للمعارف
    0.57
    ногда
    0.56
     ElementRef
    0.53
    antMatchers
    0.50
    下载附件
    0.50
     EconPapers
    0.48
    mainAxisSize
    0.47
     begyn
    0.46
     शामिल
    0.46
    titudine
    0.46
    Activations Density 11.657%

    No Known Activations