© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11478
    Prev
    Next
    INDEX
    Explanations

    sentences using auxiliary verbs such as "has", "have", "will", and "been"

    oai_token-act-pair · gemini-2.0-flash

    has

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    tagHelperRunner
    -1.02
     صوتيه
    -0.97
    rungsseite
    -0.94
     AssemblyCulture
    -0.92
    istoitu
    -0.91
    GEBURTSDATUM
    -0.91
    انيف
    -0.90
     uſed
    -0.89
     nahilalakip
    -0.88
    endforeach
    -0.88
    POSITIVE LOGITS
    nt
    0.47
    alo
    0.42
    bala
    0.41
    nter
    0.35
    ↵
    0.35
     statt
    0.35
     été
    0.35
     ה
    0.35
    <eos>
    0.34
    ho
    0.34
    Activations Density 2.005%

    No Known Activations