© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9728
    Prev
    Next
    INDEX
    Explanations

    email headers and formatting such as dates, times, email addresses, and common punctuation

    oai_token-act-pair · gemini-2.0-flash

    code or math 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
     EconPapers
    -0.79
    tvguidetime
    -0.78
    tagHelperRunner
    -0.64
    hyrchwyd
    -0.60
    Personensuche
    -0.60
     autorytatywna
    -0.57
    endphp
    -0.57
    SourceChecksum
    -0.56
     Blend
    -0.55
    ::::::::
    -0.55
    POSITIVE LOGITS
    $^{
    0.48
    arp
    0.44
    ing
    0.44
    ries
    0.43
    $^
    0.42
    }^{
    0.41
    ess
    0.40
    EDING
    0.40
    r
    0.40
    ↵
    0.39
    Activations Density 19.050%

    No Known Activations