© 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. 14381
    Prev
    Next
    INDEX
    Explanations

    words related to manufacturing semiconductors using lithography

    oai_token-act-pair · gemini-2.0-flash

    special characters and non-English words

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

    technical documentation, patents

    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
    脚注の使い方
    -1.09
    TintMode
    -0.88
    RegressionTest
    -0.82
     Мексичка
    -0.79
    basicConfig
    -0.75
     MainAxisSize
    -0.73
    utilisons
    -0.73
    RegistryLite
    -0.73
    voix
    -0.72
     StringTokenizer
    -0.71
    POSITIVE LOGITS
     special
    0.43
     asemenea
    0.41
     //
    0.39
    一眼
    0.37
    ud
    0.37
     U
    0.37
    起的
    0.37
    реза
    0.37
     "//
    0.36
     Middle
    0.36
    Activations Density 9.729%

    No Known Activations