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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6366
    Prev
    Next
    INDEX
    Explanations

    the word "meaning," and in some cases words around it

    oai_token-act-pair · gemini-2.0-flash

    meaning

    np_max-act · gemini-2.0-flash

    meaning

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     termica
    -0.71
     kysy
    -0.66
     auffi
    -0.66
     toiminta
    -0.66
     acorns
    -0.62
     Pliocene
    -0.62
     decorazione
    -0.62
     metastases
    -0.62
     elettrica
    -0.61
     trasparente
    -0.61
    POSITIVE LOGITS
    @",
    0.90
    +");
    0.77
    jsdelivr
    0.73
    JAMIN
    0.69
     end
    0.69
    ]='\
    0.68
    +',
    0.68
    جغرافيا
    0.68
     WebDriverWait
    0.67
    +",
    0.66
    Activations Density 1.833%

    No Known Activations