© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14400
    Prev
    Next
    INDEX
    Explanations

    words related to aggression and conflict, especially 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_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
    Not in Any Lists

    No Comments

    Negative Logits
     attack
    -2.48
     Attack
    -2.28
    attack
    -2.27
     attacks
    -2.19
     attacked
    -2.03
     ATTACK
    -2.03
    Attack
    -2.02
     Attacks
    -1.96
     attacking
    -1.91
    attacks
    -1.90
    POSITIVE LOGITS
    awaiter
    0.57
    }))
    0.53
    })));
    0.53
     >::
    0.51
    knapp
    0.49
    ImageContext
    0.49
     realisation
    0.48
    )))
    0.48
    ()]);
    0.47
    Ár
    0.47
    Activations Density 5.799%

    No Known Activations