© 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. 14275
    Prev
    Next
    INDEX
    Explanations

    code headers, error messages, or object oriented programming code

    oai_token-act-pair · gemini-2.0-flash

    archaic or unusual English terms

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

    Code and configurations for the neuron is detecting or predicting

    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
     l
    -0.57
     g
    -0.56
     tr
    -0.55
     
    -0.54
     may
    -0.53
     om
    -0.53
     G
    -0.52
     u
    -0.50
     L
    -0.50
     t
    -0.50
    POSITIVE LOGITS
     Efq
    1.10
     pleaſure
    1.06
     ſeveral
    1.05
     Majefty
    1.05
     myſelf
    1.03
     Monfieur
    1.02
     ―――――
    1.01
     doubtnut
    0.96
     purpoſe
    0.94
     fubject
    0.94
    Activations Density 2.736%

    No Known Activations