© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5880
    Prev
    Next
    INDEX
    Explanations

    the word "candidate", and words near it, in the context of legal documents

    oai_token-act-pair · gemini-2.0-flash

    candidate

    np_max-act · gemini-2.0-flash

    candidate

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    czerw
    -0.62
    RepeatedField
    -0.60
    TERA
    -0.59
     Pellegrini
    -0.59
     ElementRef
    -0.58
    cknow
    -0.57
    monials
    -0.57
     Lyra
    -0.56
    rijfs
    -0.56
    VERTISING
    -0.56
    POSITIVE LOGITS
    ClientSize
    0.68
     âgé
    0.67
     pitié
    0.66
     mourut
    0.66
     étoit
    0.64
     suprême
    0.64
    исленность
    0.63
     chré
    0.63
     religieuses
    0.62
     auroit
    0.61
    Activations Density 1.766%

    No Known Activations