© 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
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9413
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest an opinion or acknowledgement

    oai_token-act-pair · gemini-2.0-flash

    guess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Waray
    -0.73
    ppure
    -0.72
    bezpe
    -0.49
    : 
    -0.48
    uxley
    -0.47
    }>
    -0.46
     kasarigan
    -0.46
     везе
    -0.46
     lijn
    -0.44
    까지
    -0.44
    POSITIVE LOGITS
     StatefulWidget
    0.61
    JoinTable
    0.59
     InputDecoration
    0.57
    GenerationType
    0.56
     updatedAt
    0.56
    readystatechange
    0.55
     Quadrant
    0.55
    SpringBootTest
    0.55
    printStackTrace
    0.54
    fvar
    0.53
    Activations Density 0.192%

    No Known Activations