© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12503
    Prev
    Next
    INDEX
    Explanations

    words related to legal judgements, the process of law and specific acts.

    oai_token-act-pair · gemini-2.0-flash

    words ending with "self"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     jäsen
    -0.54
     serez
    -0.53
     démocr
    -0.52
     strå
    -0.50
     skär
    -0.50
     élevées
    -0.50
     digitais
    -0.50
     stål
    -0.48
     néz
    -0.48
     skolan
    -0.48
    POSITIVE LOGITS
     themſelves
    1.03
     myſelf
    1.02
     himſelf
    1.02
     Efq
    1.01
     ſeveral
    1.01
     whoſe
    0.98
     itſelf
    0.96
     Houſe
    0.95
     againſt
    0.93
     becauſe
    0.90
    Activations Density 58.343%

    No Known Activations