© 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. 14140
    Prev
    Next
    INDEX
    Explanations

    words or phrases relating to biological research and processes.

    oai_token-act-pair · gemini-2.0-flash

    terms related to secondary and tertiary structures

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

    protein structure

    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
     }{@
    -0.51
     remarqué
    -0.51
    HAEL
    -0.50
    CompilerServices
    -0.49
    ViewImports
    -0.49
    LLAB
    -0.49
    Портал
    -0.47
    avadoc
    -0.47
     transfieras
    -0.46
    __(/*!
    -0.46
    POSITIVE LOGITS
     tertiary
    0.94
     secondary
    0.91
    secondary
    0.89
     Tertiary
    0.80
     Secondary
    0.79
    Secondary
    0.75
     SECONDARY
    0.75
    SECONDARY
    0.73
    Tertiary
    0.70
     sekund
    0.65
    Activations Density 2.623%

    No Known Activations