© 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. 3976
    Prev
    Next
    INDEX
    Explanations

    language related to employment law

    oai_token-act-pair · gemini-2.0-flash

    terms related to accommodation

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

    Legal/employer related texts

    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
     ]];
    -0.61
    期刊论文
    -0.54
    iibo
    -0.49
     */;
    -0.48
    "]);
    -0.47
    "}"
    -0.47
     @}
    -0.46
    >>;
    -0.46
    lical
    -0.46
    apat
    -0.46
    POSITIVE LOGITS
     utafitiHapana
    0.72
     المعيارى
    0.69
    commodation
    0.69
    Accommodation
    0.66
    titleMargin
    0.66
     accommodation
    0.62
    verwijspagina
    0.60
    addContainerGap
    0.60
    Reasonable
    0.59
     Accommodation
    0.58
    Activations Density 2.025%

    No Known Activations