© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6249
    Prev
    Next
    INDEX
    Explanations

    technical writing about lab experiments and scientific classification

    oai_token-act-pair · gemini-2.0-flash

    Codes and abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     EQUIPMENT
    -0.53
     EXPERIMENTS
    -0.53
     PRESENTATION
    -0.50
     CONTRIBUTORS
    -0.50
     SUBJECTS
    -0.48
     CLASSIFICATION
    -0.48
     COUNTRIES
    -0.48
     RECOMMENDATIONS
    -0.47
     FACTORS
    -0.46
     LIBRARIES
    -0.45
    POSITIVE LOGITS
     CG
    1.02
     AK
    1.00
     CSS
    0.99
     CW
    0.98
     PC
    0.98
     VR
    0.98
     CP
    0.98
     CB
    0.98
     PS
    0.97
     CSO
    0.96
    Activations Density 30.991%

    No Known Activations