© 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. 9433
    Prev
    Next
    INDEX
    Explanations

    references to manual labor and pioneering-era California history

    oai_token-act-pair · gemini-2.0-flash

    terms related to milling or flour production

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

    mills and flour

    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
     bayonet
    -0.50
    JNIEnv
    -0.43
    structions
    -0.40
    borderSide
    -0.40
    BASEPATH
    -0.40
    ].)
    -0.40
    ագրություններ
    -0.39
    íso
    -0.39
     Ba
    -0.38
    IFORM
    -0.38
    POSITIVE LOGITS
     Paglinawan
    0.85
     mill
    0.84
     autorytatywna
    0.84
    IContainer
    0.79
     Mill
    0.75
    parsedMessage
    0.75
     miller
    0.72
     flour
    0.72
     &___
    0.72
     mil
    0.72
    Activations Density 2.176%

    No Known Activations