© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7898
    Prev
    Next
    INDEX
    Explanations

    the word "mission" and words about committing crimes

    oai_token-act-pair · gemini-2.0-flash

    mission

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    SceneManagement
    -0.62
    ſelves
    -0.61
     CGSize
    -0.59
    OrEqualTo
    -0.56
    føre
    -0.56
     Ráp
    -0.56
     Scientific
    -0.56
    monic
    -0.55
    kyou
    -0.54
    wnież
    -0.54
    POSITIVE LOGITS
    awtextra
    0.61
    MessageOf
    0.57
     ivelany
    0.52
    XmlAccessType
    0.49
    RTLD
    0.45
     насеље
    0.44
    
    0.44
     impossível
    0.43
    Mission
    0.43
     honra
    0.42
    Activations Density 0.740%

    No Known Activations