© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9437
    Prev
    Next
    INDEX
    Explanations

    clauses or phrases using the word "be" or "was" that indicate a state or duration

    oai_token-act-pair · gemini-2.0-flash

    over

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     pinulongan
    -0.69
     '\\;'
    -0.66
     typelib
    -0.65
     nonatomic
    -0.59
     Roskov
    -0.57
    iller
    -0.57
     chi̍t
    -0.54
    انتهای
    -0.53
    তথ্যসূত্র
    -0.52
    MISC
    -0.52
    POSITIVE LOGITS
     over
    2.97
    over
    2.39
     Over
    2.28
    Over
    2.27
     OVER
    2.09
    OVER
    1.81
     över
    1.73
     über
    1.51
    オーバー
    1.46
    overs
    1.35
    Activations Density 2.688%

    No Known Activations