© 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. 2449
    Prev
    Next
    INDEX
    Explanations

    words related to items, storage, and ownership in either food preparation or gardening contexts

    oai_token-act-pair · gemini-2.0-flash

    the word 'around'

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

    household chores

    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
    aluz
    -0.43
     eventdata
    -0.42
    ::::::::
    -0.40
    สบ
    -0.39
    وضوع
    -0.39
    彼
    -0.38
    oneer
    -0.37
    thy
    -0.37
    SPD
    -0.37
    TIT
    -0.37
    POSITIVE LOGITS
     around
    1.38
    around
    1.20
     Around
    1.17
    Around
    1.15
     AROUND
    1.09
    AROUND
    0.95
     alrededor
    0.92
     rundt
    0.86
     resourceCulture
    0.81
     intorno
    0.79
    Activations Density 1.300%

    No Known Activations