© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6584
    Prev
    Next
    INDEX
    Explanations

    the word "proper" and closely related words like "correct".

    oai_token-act-pair · gemini-2.0-flash

    proper

    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
    NewUrlParser
    -0.57
    freopen
    -0.50
     GlobalKey
    -0.50
    GetHashCode
    -0.49
    IVEREF
    -0.48
    Odkazy
    -0.47
    ($__
    -0.46
    DataSetChanged
    -0.45
    Földrajzportál
    -0.45
    chauss
    -0.44
    POSITIVE LOGITS
     proper
    1.28
    proper
    1.21
     correct
    1.21
    Proper
    1.14
     Proper
    1.14
     properly
    1.12
     Correct
    1.11
     correctly
    1.07
    correct
    1.06
     PROPER
    1.06
    Activations Density 1.307%

    No Known Activations