© 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. 8295
    Prev
    Next
    INDEX
    Explanations

    abbreviations that denote legal citations, particularly those including J or JJ, likely referencing judges

    oai_token-act-pair · gemini-2.0-flash

    Legal citations

    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
     raiſ
    -1.15
     ſtate
    -1.13
    ſelf
    -1.11
     pleaſure
    -1.09
     purpoſe
    -1.09
     houſe
    -1.09
     deſt
    -1.07
     ſur
    -1.05
     tranſ
    -1.04
     Majefty
    -1.03
    POSITIVE LOGITS
     S
    0.99
     M
    0.98
     R
    0.96
     A
    0.96
     N
    0.95
     F
    0.94
     C
    0.94
     P
    0.93
     B
    0.93
     Q
    0.92
    Activations Density 5.182%

    No Known Activations