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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14575
    Prev
    Next
    INDEX
    Explanations

    statements about how something hurts a group of people

    oai_token-act-pair · gemini-2.0-flash

    victims

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     victim
    -2.55
     victims
    -2.22
     Victim
    -2.19
    victim
    -2.19
     Victims
    -2.11
    Victim
    -1.95
     victime
    -1.83
     victimes
    -1.77
     víctima
    -1.62
     vítima
    -1.60
    POSITIVE LOGITS
    oneofs
    0.70
     ujednoznacz
    0.55
    TestingModule
    0.54
    webElementXpaths
    0.54
     actionMode
    0.53
    ArrowToggle
    0.53
    OptionsMenu
    0.52
     الدولى
    0.52
     صوتيه
    0.51
    ẵn
    0.51
    Activations Density 3.652%

    No Known Activations