© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3475
    Prev
    Next
    INDEX
    Explanations

    sentences containing the words "that," "who," "which", "it", "they", or "you."

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     and
    -0.79
     within
    -0.56
     inside
    -0.55
     outside
    -0.54
     under
    -0.53
     (
    -0.48
     \&
    -0.48
     beyond
    -0.47
    ніципалі
    -0.46
     across
    -0.45
    POSITIVE LOGITS
    '
    0.86
     Shakspeare
    0.85
    ’
    0.77
     perfons
    0.69
     Jefus
    0.68
     Shaksp
    0.67
     Esau
    0.66
     Latinos
    0.65
     greateſt
    0.64
     Cæsar
    0.63
    Activations Density 4.262%

    No Known Activations