© 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. 6769
    Prev
    Next
    INDEX
    Explanations

    instances of harmful attacks

    oai_token-act-pair · gemini-2.0-flash

    attack

    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
     attack
    -2.88
     Attack
    -2.56
     attacks
    -2.53
    attack
    -2.39
     ATTACK
    -2.30
     attacked
    -2.28
    Attack
    -2.28
     Attacks
    -2.20
     ataque
    -2.08
     attacking
    -2.06
    POSITIVE LOGITS
     myſelf
    0.83
    parsedMessage
    0.73
    SWIG
    0.73
     paging
    0.70
     Theſe
    0.68
     виправивши
    0.68
    Sucesor
    0.68
    brite
    0.67
     BUREAU
    0.65
    ElementException
    0.64
    Activations Density 0.355%

    No Known Activations