© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11563
    Prev
    Next
    INDEX
    Explanations

    technical language to do with systems and performance, or high and low

    oai_token-act-pair · gemini-2.0-flash

    technical performance attributes

    np_token-act-pair-logits · gpt-4o-mini

    technology improvements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     المعيارى
    -0.79
    تقاوى
    -0.66
    ollectionView
    -0.66
    المناصب
    -0.65
     Signalez
    -0.63
    RectangleBorder
    -0.61
    rungsseite
    -0.60
     BoxFit
    -0.58
    Hochspringen
    -0.57
    })));
    -0.54
    POSITIVE LOGITS
    queryInterface
    0.66
     performance
    0.61
     isInitialized
    0.54
     reliability
    0.53
    giveness
    0.53
     usability
    0.52
     operational
    0.52
    Effectiveness
    0.51
     Usability
    0.49
    SequentialGroup
    0.49
    Activations Density 2.236%

    No Known Activations