© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9267
    Prev
    Next
    INDEX
    Explanations

    legal language, particularly related to court proceedings, and legal definitions

    oai_token-act-pair · gemini-2.0-flash

    legal terminology or jargon

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

    legal documents and cases

    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
    ècie
    -0.60
    ]")]
    -0.60
    Gradu
    -0.58
    erapeutics
    -0.56
    umerable
    -0.56
    Tracce
    -0.54
    essai
    -0.54
    extAlignment
    -0.54
    anyahu
    -0.53
    agisse
    -0.53
    POSITIVE LOGITS
     Normdatei
    0.51
     дописавши
    0.50
    tableFuture
    0.50
    noten
    0.49
    \{\\
    0.47
    machte
    0.47
     وصلة
    0.46
    execSQL
    0.43
    nă
    0.42
    DJANGO
    0.42
    Activations Density 3.053%

    No Known Activations