© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1726
    Prev
    Next
    INDEX
    Explanations

    titles and the words that come just after "The"

    oai_token-act-pair · gemini-2.0-flash

    The

    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
     like
    -0.43
    最快更新
    -0.43
    ﴿
    -0.41
    +#+
    -0.39
     *}
    -0.39
    ̲
    -0.38
    存于互联网档案馆
    -0.36
    like
    -0.36
     diken
    -0.36
     {(
    -0.36
    POSITIVE LOGITS
    msgSender
    0.64
    saurus
    0.64
     Réponses
    0.63
    Referencies
    0.63
    TargetException
    0.62
    كامل
    0.61
     kasarigan
    0.61
     noqa
    0.60
     Serap
    0.59
     pleaſure
    0.59
    Activations Density 5.488%

    No Known Activations