© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8992
    Prev
    Next
    INDEX
    Explanations

    words that describe something being challenging or difficult to obtain

    oai_token-act-pair · gemini-2.0-flash

    difficult or complex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     easy
    -0.75
     easier
    -0.74
     easily
    -0.73
    easy
    -0.68
     könny
    -0.67
     łat
    -0.67
     Easily
    -0.65
    easily
    -0.64
     dễ
    -0.63
     Easy
    -0.63
    POSITIVE LOGITS
     difficult
    0.96
     complex
    0.96
    difficult
    0.93
     complicated
    0.90
     Difficult
    0.90
    Difficult
    0.87
     expensive
    0.83
    Complex
    0.82
     Complex
    0.80
    complex
    0.80
    Activations Density 2.651%

    No Known Activations