© 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. 8844
    Prev
    Next
    INDEX
    Explanations

    words associated with violent crime and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    Negative events

    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
     الرياضيه
    -0.76
    RTLD
    -0.64
    хьтан
    -0.62
    WriteBarrier
    -0.59
     transférez
    -0.54
     Roskov
    -0.54
     ujednoznacz
    -0.54
    elemField
    -0.54
    StreetMap
    -0.54
    complexContent
    -0.54
    POSITIVE LOGITS
    (©
    0.57
     insuffisamment
    0.57
    ^(@)
    0.55
    rítica
    0.54
     становника
    0.52
     passed
    0.52
    Downloaded
    0.50
     Mots
    0.50
     rests
    0.49
    ſelf
    0.49
    Activations Density 6.804%

    No Known Activations