© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13783
    Prev
    Next
    INDEX
    Explanations

    mentions of screaming, yelling, or otherwise vocally expressing emotion, and related words such as frightened or teeth.

    oai_token-act-pair · gemini-2.0-flash

    shouting, 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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    anthene
    -0.56
    RenderAtEndOf
    -0.55
     '\\;'
    -0.55
    hest
    -0.50
    PhysRevLett
    -0.48
    GenerationType
    -0.48
    __).
    -0.48
     Gra
    -0.47
    GroupLayout
    -0.47
    matu
    -0.47
    POSITIVE LOGITS
     AppCompatTheme
    0.73
     AttributeSet
    0.62
     caufe
    0.57
     doPost
    0.55
    cnica
    0.53
    EndInit
    0.52
    TextSpan
    0.52
    Forrás
    0.52
     Universitario
    0.52
    Fotó
    0.52
    Activations Density 1.599%

    No Known Activations