© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9481
    Prev
    Next
    INDEX
    Explanations

    mentions of head and injuries/violence

    oai_token-act-pair · gemini-2.0-flash

    head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     head
    -1.56
    Head
    -1.55
     Head
    -1.54
    head
    -1.45
     heads
    -1.39
    HEAD
    -1.39
     HEAD
    -1.35
     Heads
    -1.29
    heads
    -1.22
    Heads
    -1.19
    POSITIVE LOGITS
    zyst
    0.48
    elerik
    0.45
     때문
    0.43
    áctenos
    0.42
    munic
    0.41
    arela
    0.41
    Kariera
    0.41
     McCa
    0.41
    unov
    0.41
    licants
    0.40
    Activations Density 11.640%

    No Known Activations