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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7316
    Prev
    Next
    INDEX
    Explanations

    scientific documents mentioning axes, directions, and currents

    oai_token-act-pair · gemini-2.0-flash

    axis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    MLLoader
    -1.08
     Normdatei
    -0.89
    MessageTagHelper
    -0.80
    клопе
    -0.75
     AssemblyCulture
    -0.75
     الحره
    -0.74
     كومونز
    -0.73
     صوتيه
    -0.70
     kasarigan
    -0.70
     وتسجيلات
    -0.69
    POSITIVE LOGITS
     itſelf
    1.44
     Reſ
    1.29
     Houſe
    1.26
     Majefty
    1.23
     myſelf
    1.20
     Conſ
    1.20
     houſe
    1.17
     Jefus
    1.16
     Anſ
    1.16
     Monfieur
    1.16
    Activations Density 1.604%

    No Known Activations