© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2364
    Prev
    Next
    INDEX
    Explanations

    uses of the word "you" and words referring to groups of people like "people" or "population"

    oai_token-act-pair · gemini-2.0-flash

    identification

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    BeginContext
    -0.87
    twimg
    -0.62
    __(/*!
    -0.60
     يتيمه
    -0.58
    addCriterion
    -0.57
    DeleteBehavior
    -0.57
    writeFieldEnd
    -0.56
    exels
    -0.55
     kaynağından
    -0.53
    MIDDLEWARE
    -0.52
    POSITIVE LOGITS
     identification
    2.63
     identify
    2.59
     identified
    2.52
     identifying
    2.48
     Identification
    2.45
    identify
    2.45
     identifies
    2.39
     Identify
    2.38
     Identifying
    2.36
    Identification
    2.31
    Activations Density 4.687%

    No Known Activations