© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12136
    Prev
    Next
    INDEX
    Explanations

    json-like data structures.

    oai_token-act-pair · gemini-2.0-flash

    colons, quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    
    -0.79
    Portail
    -0.71
     LZ
    -0.66
    فایل‌لار
    -0.63
    IsMutable
    -0.63
     للمعارف
    -0.62
    Geplaatst
    -0.61
    ContentAsync
    -0.60
     Sciento
    -0.60
    GEBURTSDATUM
    -0.59
    POSITIVE LOGITS
    ValueGeneration
    0.52
    ständig
    0.49
     litté
    0.49
    füllen
    0.47
    omitempty
    0.46
    inosi
    0.45
     financières
    0.45
     we
    0.44
    IALS
    0.43
     "",
    
    0.43
    Activations Density 0.795%

    No Known Activations