© 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. 2809
    Prev
    Next
    INDEX
    Explanations

    scientific vocabulary related to chemistry and materials.

    oai_token-act-pair · gemini-2.0-flash

    terms related to matrices

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

    matrix

    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
    GIH
    -0.55
    apimachinery
    -0.55
    styleType
    -0.54
     Argyle
    -0.52
    hoga
    -0.52
    ADELPHIA
    -0.51
     ddelweddau
    -0.51
    vité
    -0.51
     Bleach
    -0.50
    ագրություններ
    -0.50
    POSITIVE LOGITS
     matrix
    1.27
     matrices
    1.09
    matrix
    1.02
     Matrix
    0.99
     Matrices
    0.93
     matriz
    0.88
     matrice
    0.87
    matrices
    0.85
    Matrix
    0.84
     матри
    0.83
    Activations Density 2.940%

    No Known Activations