© 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. 12216
    Prev
    Next
    INDEX
    Explanations

    code block delimiters and file paths, especially related to defining configuration settings.

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    
    -0.59
    <bos>
    -0.59
    '].'
    -0.55
    glise
    -0.54
    awtextra
    -0.54
     دریافت‌شده
    -0.51
     esternos
    -0.50
    [__
    -0.50
     merits
    -0.50
    Спољашње
    -0.49
    POSITIVE LOGITS
     Banker
    0.45
     BoxFit
    0.44
    forName
    0.41
     minutter
    0.40
     ujednoznacz
    0.40
     contextLoads
    0.37
     Collision
    0.37
    <?
    0.37
    fromnode
    0.37
     gentes
    0.36
    Activations Density 0.822%

    No Known Activations