© 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. 5217
    Prev
    Next
    INDEX
    Explanations

    the word "still" followed by other words that indicate a continuing state

    oai_token-act-pair · gemini-2.0-flash

    words that start with 'still'

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

    still

    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
     still
    -3.44
    Still
    -3.14
    still
    -3.13
     Still
    -3.09
     STILL
    -2.53
    STILL
    -2.38
     todavía
    -2.27
     ainda
    -2.20
     ancora
    -2.17
     masih
    -2.09
    POSITIVE LOGITS
     Италијани
    0.65
    ratislava
    0.65
    BeginContext
    0.61
     appelez
    0.60
    GEBURTSDATUM
    0.59
    setAccessible
    0.59
    intios
    0.58
     onCreateView
    0.57
    ClientSize
    0.57
     =>
    0.57
    Activations Density 0.909%

    No Known Activations