© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15734
    Prev
    Next
    INDEX
    Explanations

    common phrases that include "in", "thing", "keep", or "bear"

    oai_token-act-pair · gemini-2.0-flash

    say "in"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ⓧ
    -0.59
     وتسجيلات
    -0.52
    fromUtf
    -0.50
    اند
    -0.49
    lete
    -0.49
     بيها
    -0.49
    nter
    -0.48
     ujednoznacz
    -0.48
     <",
    -0.47
    anga
    -0.47
    POSITIVE LOGITS
     in
    0.76
    complexContent
    0.71
    PullParser
    0.67
     In
    0.62
     Penh
    0.60
    In
    0.59
     Winaray
    0.56
     avoient
    0.55
    getIn
    0.54
     IN
    0.54
    Activations Density 0.753%

    No Known Activations