© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1605
    Prev
    Next
    INDEX
    Explanations

    labels with a lot of punctuation and random characters

    oai_token-act-pair · gemini-2.0-flash

    colon

    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
     AssemblyTitle
    -0.52
     receitas
    -0.46
     revenues
    -0.44
     accounts
    -0.41
     revenue
    -0.41
    ff
    -0.40
    profit
    -0.39
    Politique
    -0.38
     balances
    -0.38
     EoL
    -0.38
    POSITIVE LOGITS
    kuuta
    0.79
     Roskov
    0.75
     发表于
    0.74
    Aktualisiert
    0.73
    Erreferentziak
    0.71
    AndEndTag
    0.69
    Lähteet
    0.68
    Độ
    0.64
    bewerken
    0.63
    QApplication
    0.63
    Activations Density 0.589%

    No Known Activations