© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 563
    Prev
    Next
    INDEX
    Explanations

    words related to the degree to which people are willing to do things, and also finds filler words like "that" or "the."

    oai_token-act-pair · gemini-2.0-flash

    Superscript notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     sacrifice
    -1.93
     sacrifices
    -1.73
     sacrificed
    -1.73
     sacrificing
    -1.69
    sacrific
    -1.68
     Sacrifice
    -1.68
     Sacrific
    -1.66
    sacrifice
    -1.57
     sacrificial
    -1.52
     sacrific
    -1.48
    POSITIVE LOGITS
     ^
    1.59
    <sup>
    1.44
    }^
    1.38
    }^{
    1.33
    $^
    1.25
     ^^
    1.23
    ^^
    1.20
     '^
    1.20
     ^(
    1.16
     "^
    1.15
    Activations Density 2.679%

    No Known Activations