© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4400
    Prev
    Next
    INDEX
    Explanations

    instances of protection from harm or threats

    oai_token-act-pair · gemini-2.0-flash

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     disambiguazione
    -0.63
    postsleuth
    -0.61
    
    -0.59
    typeparam
    -0.57
    fortawesome
    -0.56
    Xna
    -0.55
    rungsseite
    -0.55
    "],
    -0.54
    mobileqq
    -0.53
    IntoConstraints
    -0.53
    POSITIVE LOGITS
     Roskov
    0.72
    AndroidJUnit
    0.68
    WireFormatLite
    0.67
     lente
    0.59
    rawDesc
    0.58
    RTSC
    0.57
    ="#
    0.53
    BeginContext
    0.51
     suel
    0.50
     Caine
    0.49
    Activations Density 8.950%

    No Known Activations