© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12636
    Prev
    Next
    INDEX
    Explanations

    various forms of references to other data in a document

    oai_token-act-pair · 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
    setof
    -0.72
     تضيفلها
    -0.60
    GenerationType
    -0.54
    InjectAttribute
    -0.53
    endphp
    -0.52
    <bos>
    -0.51
    andExpect
    -0.50
     gemak
    -0.50
    hette
    -0.49
    عف
    -0.48
    POSITIVE LOGITS
     Walkover
    0.71
     kasarigan
    0.60
     magasiner
    0.58
     Infórmanos
    0.57
    ')):
    0.54
    copal
    0.52
    Enllaces
    0.52
    دانشنامهٔ
    0.51
    UIApplication
    0.51
    》.
    0.51
    Activations Density 0.334%

    No Known Activations