© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13200
    Prev
    Next
    INDEX
    Explanations

    references to case numbers in legal documents

    oai_token-act-pair · gemini-2.0-flash

    words with archaic spellings or forms

    np_token-act-pair-logits · gpt-4o-mini
    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
     EconPapers
    -0.77
     Roskov
    -0.74
     kaarangay
    -0.61
    EndInit
    -0.60
     unknownFields
    -0.60
     كومونز
    -0.59
     hObject
    -0.57
    Corollary
    -0.57
    StoryboardSegue
    -0.56
    rungsseite
    -0.55
    POSITIVE LOGITS
     Theſe
    0.71
     myſelf
    0.71
     itſelf
    0.63
     Efq
    0.58
     leaſt
    0.57
     whoſe
    0.57
    leſs
    0.56
     Jefus
    0.56
     faſt
    0.56
     Monfieur
    0.56
    Activations Density 4.613%

    No Known Activations