© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5957
    Prev
    Next
    INDEX
    Explanations

    the word 'find', 'locate' and 'finding' and words closely associated with trains in the context of mathematics

    oai_token-act-pair · gemini-2.0-flash

    find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     find
    -2.27
    find
    -2.17
     finding
    -2.09
    finding
    -2.06
     FIND
    -2.06
     finds
    -2.03
     Finding
    -2.03
    FIND
    -1.98
     Find
    -1.98
    Find
    -1.98
    POSITIVE LOGITS
    ReusableCell
    0.50
    chengladbach
    0.48
    Cyfarwyddwr
    0.47
    Примечания
    0.46
    المكان
    0.42
    utnik
    0.42
     гг
    0.41
    endregion
    0.40
    orsese
    0.40
    uhkan
    0.39
    Activations Density 0.847%

    No Known Activations