© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8228
    Prev
    Next
    INDEX
    Explanations

    the prefix "respon"

    oai_token-act-pair · 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
    RenderAtEndOf
    -0.66
     AttributeSet
    -0.66
     mergeFrom
    -0.64
    reportWebVitals
    -0.61
    Chham
    -0.61
    yntaxException
    -0.59
    PhysRev
    -0.59
     Plots
    -0.57
     plots
    -0.56
    coarse
    -0.56
    POSITIVE LOGITS
    is
    0.52
    
    0.49
    :✨
    0.45
     sibi
    0.43
     dedans
    0.43
    isAlive
    0.42
    mbols
    0.42
     Normdatei
    0.40
    sibili
    0.40
    criptive
    0.39
    Activations Density 1.280%

    No Known Activations