© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4583
    Prev
    Next
    INDEX
    Explanations

    words and phrases dealing with conflict, violence, and harmful situations

    oai_token-act-pair · gemini-2.0-flash

    attacks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Pingback
    -0.55
     GetComponent
    -0.54
     Tent
    -0.54
    Oneof
    -0.51
     setInterval
    -0.50
    //{
    -0.49
     Stands
    -0.49
     gym
    -0.48
     Leonid
    -0.48
     îng
    -0.48
    POSITIVE LOGITS
    <bos>
    1.34
     attack
    0.98
     Attack
    0.91
    attack
    0.89
    Attack
    0.85
     attacking
    0.84
     attacks
    0.81
     ATTACK
    0.80
     attacked
    0.77
    ATTACK
    0.76
    Activations Density 1.618%

    No Known Activations