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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9960
    Prev
    Next
    INDEX
    Explanations

    words typically found in police reports and legal arguments

    oai_token-act-pair · gemini-2.0-flash

    legal jargon related to cases and settlements

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

    legal, prosecution

    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
    rrggbb
    -0.87
    expandindo
    -0.83
    EDEFAULT
    -0.79
    ResumeLayout
    -0.73
    InjectAttribute
    -0.72
     ddelweddau
    -0.72
    ंदीखरीदारी
    -0.70
     OFDb
    -0.70
    ValueStyle
    -0.68
    Tikang
    -0.65
    POSITIVE LOGITS
    tagext
    0.60
    DataAnnotations
    0.47
    fjspx
    0.43
     settlement
    0.41
     settled
    0.40
    клопе
    0.39
    xdb
    0.37
    iento
    0.37
     settlements
    0.35
    Artículo
    0.35
    Activations Density 3.399%

    No Known Activations