© 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. 7944
    Prev
    Next
    INDEX
    Explanations

    fragments of non-English words with a specific combination of characters

    oai_token-act-pair · gemini-2.0-flash

    ್

    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
    Geplaatst
    -1.06
     referenties
    -0.84
    ſhip
    -0.83
    BrowserModule
    -0.80
     disambiguazione
    -0.80
     pinulongan
    -0.77
    leſs
    -0.77
    ftances
    -0.76
    ')}
    -0.74
    ']>
    -0.73
    POSITIVE LOGITS
     spalle
    0.71
     enkelte
    0.71
     automatiques
    0.68
     leão
    0.67
     positifs
    0.66
     olsa
    0.66
     piele
    0.66
     picioare
    0.65
     aikaa
    0.65
     spécifiques
    0.65
    Activations Density 0.974%

    No Known Activations