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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6686
    Prev
    Next
    INDEX
    Explanations

    turns of phrase where something "turns out" to be the case

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "turn"

    np_token-act-pair-logits · gpt-4o-mini

    turn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     препратки
    -0.71
     للاسماء
    -0.66
     doInBackground
    -0.65
    reportWebVitals
    -0.61
    glLoadIdentity
    -0.60
    borderSide
    -0.58
    Pautan
    -0.56
    expandindo
    -0.53
    الدراسه
    -0.51
     onAnimation
    -0.51
    POSITIVE LOGITS
     turns
    3.09
     turn
    2.92
     turned
    2.88
    turns
    2.64
    turn
    2.61
     Turned
    2.61
     Turns
    2.56
     turning
    2.53
     Turn
    2.48
    Turned
    2.47
    Activations Density 2.887%

    No Known Activations