© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1871
    Prev
    Next
    INDEX
    Explanations

    legal language, especially terms related to courts, claims, and petitions

    oai_token-act-pair · gemini-2.0-flash

    technical or legal terms

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

    legal arguments

    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
    RenderAtEndOf
    -0.87
     CreateTagHelper
    -0.68
    setScene
    -0.58
    LLocation
    -0.56
    WithIOException
    -0.55
     opérateur
    -0.54
    cèse
    -0.53
     typelib
    -0.53
    SharedCtor
    -0.50
    BlockPos
    -0.50
    POSITIVE LOGITS
    ึ่ง
    0.61
    arture
    0.57
     distinction
    0.55
     referrerpolicy
    0.54
    >--}}
    0.53
     fakt
    0.52
    >-->
    0.52
    fact
    0.52
    icolon
    0.51
    tetés
    0.50
    Activations Density 7.661%

    No Known Activations