© 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. 12715
    Prev
    Next
    INDEX
    Explanations

    language pertaining to scientific research, studies and making associations between concepts

    oai_token-act-pair · gemini-2.0-flash

    scientific studies

    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
    providedIn
    -0.69
    </thead>
    -0.68
     defaultstate
    -0.68
     Económica
    -0.66
    tonsoft
    -0.66
     оригіналу
    -0.65
     RoutedEventArgs
    -0.64
     跳转至
    -0.61
    /**
    -0.59
     snippetHide
    -0.58
    POSITIVE LOGITS
     lenker
    0.53
     الرياضيه
    0.51
     Tal
    0.50
    skel
    0.48
    ControllerTest
    0.48
    ystema
    0.48
    beled
    0.48
    неопр
    0.46
     gra
    0.45
     tak
    0.44
    Activations Density 0.918%

    No Known Activations