© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4790
    Prev
    Next
    INDEX
    Explanations

    language predictive of academic studies

    oai_token-act-pair · gemini-2.0-flash

    research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     METHODOLOGY
    -0.70
    Methodology
    -0.68
     Methodology
    -0.62
    METHODOLOGY
    -0.61
     Réponses
    -0.60
     WaitForSeconds
    -0.59
    ราะ
    -0.57
    Tikang
    -0.55
     DIAGRAM
    -0.55
     doInBackground
    -0.54
    POSITIVE LOGITS
     initComponents
    0.57
    mpä
    0.56
    thâu
    0.55
    AntiForgeryToken
    0.53
    IPAC
    0.50
    ParallelGroup
    0.50
     cucchia
    0.48
     Roskov
    0.47
    principalTable
    0.47
     lobbies
    0.47
    Activations Density 8.491%

    No Known Activations