© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13964
    Prev
    Next
    INDEX
    Explanations

    instances of needing to do something

    oai_token-act-pair · gemini-2.0-flash

    need

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     will
    -0.65
     "
    -0.64
     “
    -0.63
     in
    -0.59
     
    -0.58
     re
    -0.57
     section
    -0.55
     program
    -0.55
     modern
    -0.54
     is
    -0.53
    POSITIVE LOGITS
     متعلقه
    1.47
    ThroughAttribute
    1.33
    Personendaten
    1.29
    GEBURTSDATUM
    1.23
     незавершена
    1.18
     فريبيس
    1.15
     nakalista
    1.15
     JpaRepository
    1.13
    IsMutable
    1.05
     تضيفلها
    1.05
    Activations Density 0.499%

    No Known Activations