© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10823
    Prev
    Next
    INDEX
    Explanations

    the word "originally" and concepts semantically similar to 'formerly'

    oai_token-act-pair · gemini-2.0-flash

    originally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     originally
    -1.56
    originally
    -1.38
    Originally
    -1.19
     originalmente
    -1.19
     Originally
    -1.13
     initially
    -1.01
     inicialmente
    -0.93
     ursprünglich
    -0.90
    <bos>
    -0.85
    previously
    -0.85
    POSITIVE LOGITS
    AutoScaleMode
    0.57
     general
    0.57
     sein
    0.56
     final
    0.56
    ParallelGroup
    0.55
     official
    0.55
    Insee
    0.55
     true
    0.55
     Sinha
    0.54
    كات
    0.54
    Activations Density 1.896%

    No Known Activations