© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14426
    Prev
    Next
    INDEX
    Explanations

    expressions that suggest considering perspectives or personal opinions about a topic

    oai_token-act-pair · gemini-2.0-flash

    feelings/behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     للمعارف
    -1.05
    Personendaten
    -0.94
     why
    -0.81
    why
    -0.77
    Personensuche
    -0.74
     Warum
    -0.73
     Why
    -0.73
    Why
    -0.73
     Pourquoi
    -0.71
    InjectAttribute
    -0.68
    POSITIVE LOGITS
    sprechend
    0.54
    )')
    0.52
    GHIJKLM
    0.47
     MatDialog
    0.46
     ویکی‌پدیای
    0.45
     kep
    0.44
    มาะ
    0.44
    AutoresizingMask
    0.44
    
    0.43
    frost
    0.43
    Activations Density 0.648%

    No Known Activations