© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8580
    Prev
    Next
    INDEX
    Explanations

    references to legislative bodies

    oai_token-act-pair · gemini-2.0-flash

    Assembly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     kasarigan
    -0.75
     nuits
    -0.57
    فحة
    -0.52
    Kreis
    -0.50
     cherchés
    -0.48
    hoon
    -0.47
    ಃ
    -0.47
     professionnelle
    -0.46
     Púb
    -0.46
     fecond
    -0.46
    POSITIVE LOGITS
    ContentAsync
    0.75
    brainly
    0.73
    endphp
    0.69
    enterOuterAlt
    0.65
    Према
    0.65
    chtig
    0.55
    SaveChangesAsync
    0.55
    BASEPATH
    0.54
    StandardCharsets
    0.53
    riwal
    0.53
    Activations Density 1.136%

    No Known Activations