© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1890
    Prev
    Next
    INDEX
    Explanations

    the letter "O" followed by an apostrophe

    oai_token-act-pair · gemini-2.0-flash

    O

    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
    tvguidetime
    -0.91
     nakalista
    -0.85
    featureID
    -0.84
     שוליים
    -0.83
     دیکھیے
    -0.82
    Tikang
    -0.81
    kháu
    -0.79
    XmlAccessorType
    -0.79
     initComponents
    -0.77
    WriteTagHelper
    -0.77
    POSITIVE LOGITS
    eller
    0.45
    eland
    0.43
    ella
    0.42
    tid
    0.42
    pper
    0.42
    udar
    0.42
    vend
    0.41
    gas
    0.41
    icken
    0.41
    ishi
    0.41
    Activations Density 0.435%

    No Known Activations