© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15857
    Prev
    Next
    INDEX
    Explanations

    language related to judicial authority or the act of legally possessing something

    oai_token-act-pair · gemini-2.0-flash

    jurisdiction, legal authority

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    PerformLayout
    -0.82
    IndentedString
    -0.70
    AndEndTag
    -0.70
    SharedCtor
    -0.69
    WriteAttribute
    -0.68
     الرياضيه
    -0.65
    例句
    -0.63
    HasForeignKey
    -0.60
    NewUrlParser
    -0.59
    scrapy
    -0.59
    POSITIVE LOGITS
    entile
    0.56
     يتيمه
    0.55
    Портал
    0.49
     statutory
    0.46
    gestellten
    0.45
     vertical
    0.45
     special
    0.45
     the
    0.44
     certain
    0.44
     equivalent
    0.44
    Activations Density 2.430%

    No Known Activations