© 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. 9486
    Prev
    Next
    INDEX
    Explanations

    mentions of things are unique or distinctive

    oai_token-act-pair · gemini-2.0-flash

    special

    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
     special
    -3.11
    Special
    -2.86
     Special
    -2.83
    special
    -2.81
     speciale
    -2.42
     SPECIAL
    -2.39
    SPECIAL
    -2.33
     especial
    -2.06
     speciali
    -2.00
     spéciale
    -1.95
    POSITIVE LOGITS
    amemnon
    0.70
    ChildScrollView
    0.62
    ără
    0.60
    ualaikum
    0.60
    
    0.58
    ocellular
    0.55
    itchfield
    0.55
    expandindo
    0.54
    EDEFAULT
    0.54
    )|^{
    0.54
    Activations Density 0.957%

    No Known Activations