© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11796
    Prev
    Next
    INDEX
    Explanations

    the word "secure", "secured" and "accepting"

    oai_token-act-pair · gemini-2.0-flash

    secure

    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
    Not in Any Lists

    No Comments

    Negative Logits
     réguli
    -0.74
     définiti
    -0.73
     fédé
    -0.72
     rempliss
    -0.68
     juridiques
    -0.66
     efficaces
    -0.64
     attirer
    -0.63
     chré
    -0.63
     mérit
    -0.62
     rappeler
    -0.61
    POSITIVE LOGITS
     חיצוניים
    0.62
     Shakspeare
    0.61
    UnusedPrivate
    0.60
     plebis
    0.58
     myſelf
    0.57
    ImageField
    0.57
     snippetHide
    0.57
     unif
    0.57
     Shaksp
    0.56
     conflic
    0.56
    Activations Density 0.409%

    No Known Activations