© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6301
    Prev
    Next
    INDEX
    Explanations

    words related to emotional or violent events

    oai_token-act-pair · gemini-2.0-flash

    screaming and other expressions of distress

    np_token-act-pair-logits · gpt-4o-mini

    screaming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    astéroïdes
    -0.81
     Italijani
    -0.64
     fubject
    -0.64
    mobileqq
    -0.63
    rrggbb
    -0.62
    IndentedString
    -0.60
     ostavi
    -0.60
     groote
    -0.57
    )_/¯
    -0.56
    quelize
    -0.55
    POSITIVE LOGITS
     out
    0.60
     in
    0.51
    getOut
    0.50
    षण
    0.49
    מיד
    0.48
     into
    0.45
    riture
    0.45
     viewType
    0.44
     when
    0.44
     تضيفلها
    0.44
    Activations Density 5.344%

    No Known Activations