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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 15708
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to participation in surveys and studies

    oai_token-act-pair · gemini-2.0-flash

    engagement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     I
    -0.74
    '
    -0.68
     and
    -0.65
    }),
    
    -0.65
     or
    -0.64
    <bos>
    -0.63
     but
    -0.63
     so
    -0.63
    ]:
    
    -0.63
    .]
    -0.62
    POSITIVE LOGITS
     Majefty
    1.83
     houſe
    1.82
     Monfieur
    1.79
     ſtate
    1.73
     Efq
    1.70
     myſelf
    1.70
     Reſ
    1.70
     ſta
    1.69
     Houſe
    1.66
     ſch
    1.64
    Activations Density 3.127%

    No Known Activations