© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11448
    Prev
    Next
    INDEX
    Explanations

    names and terms used in legal settings and documents

    oai_token-act-pair · gemini-2.0-flash

    legal documents/transcripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     råd
    -0.44
    rosin
    -0.43
    activate
    -0.41
    <eos>
    -0.39
     о
    -0.39
    acti
    -0.39
    sedia
    -0.38
     beyaz
    -0.38
     buah
    -0.37
     rentrée
    -0.37
    POSITIVE LOGITS
     itſelf
    0.89
     myſelf
    0.82
    ScopeManager
    0.82
     himſelf
    0.80
    '])->
    0.76
     ――――――――
    0.75
     ―――――
    0.75
    ollectionView
    0.75
     themſelves
    0.74
     Diſ
    0.72
    Activations Density 3.007%

    No Known Activations