© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8875
    Prev
    Next
    INDEX
    Explanations

    words related to arguments and court cases

    oai_token-act-pair · gemini-2.0-flash

    Formal language/medical legal contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     themſelves
    -1.02
     Majefty
    -0.97
     purpoſe
    -0.95
     greateſt
    -0.92
     whoſe
    -0.90
     becauſe
    -0.89
     himſelf
    -0.89
     ſever
    -0.86
     Reſ
    -0.86
     raiſ
    -0.84
    POSITIVE LOGITS
     estampa
    0.39
    labelledby
    0.38
     Heist
    0.36
    ﴿
    0.36
     
    0.34
     synap
    0.34
    TargetException
    0.34
    ?
    0.33
     serena
    0.33
    TintMode
    0.32
    Activations Density 14.312%

    No Known Activations