© 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. 15250
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal proceedings and judgements.

    oai_token-act-pair · gemini-2.0-flash

    legal terminology and context

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

    legal issues and violations

    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
    lofen
    -0.56
     ddelweddau
    -0.51
    ulemon
    -0.50
     gigante
    -0.49
    lujah
    -0.48
     Anfitrión
    -0.46
     eriş
    -0.45
    epam
    -0.45
    icle
    -0.44
    chitz
    -0.44
    POSITIVE LOGITS
     Roskov
    0.67
     ExecuteAsync
    0.61
    StoreMessageInfo
    0.61
     invokingState
    0.60
    cdef
    0.60
    期刊论文
    0.59
    interopRequire
    0.58
    __*/
    0.58
     even
    0.58
    archiviato
    0.57
    Activations Density 13.517%

    No Known Activations