© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15071
    Prev
    Next
    INDEX
    Explanations

    technical research papers in chemistry, biology or medicine

    oai_token-act-pair · gemini-2.0-flash

    terms related to efficiency and performance metrics

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

    Scientific measurements and data

    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
     Signalez
    -0.66
     jspb
    -0.63
    ValueStyle
    -0.62
    fromnode
    -0.62
    URLException
    -0.61
     StatefulWidget
    -0.57
    脚注の使い方
    -0.56
    errHandler
    -0.54
     onView
    -0.52
    tvguidetime
    -0.52
    POSITIVE LOGITS
     purity
    0.54
     polarity
    0.53
     yield
    0.52
     gainera
    0.50
     efficiency
    0.50
     formation
    0.50
     reproducibility
    0.49
    setContent
    0.47
    Buildable
    0.47
    +:+
    0.46
    Activations Density 6.712%

    No Known Activations