© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9485
    Prev
    Next
    INDEX
    Explanations

    the word "attorney" in the context of the legal process

    oai_token-act-pair · gemini-2.0-flash

    attorney

    np_max-act · gemini-2.0-flash
    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
    GARET
    -0.63
     we
    -0.62
     "
    -0.60
     We
    -0.59
     ...
    -0.59
     …
    -0.57
    ので
    -0.57
    We
    -0.56
    ...@
    -0.56
     ^
    -0.53
    POSITIVE LOGITS
     Efq
    1.17
     Monfieur
    1.05
     myſelf
    1.01
     faſt
    0.93
    providedIn
    0.93
     ſche
    0.91
     fubject
    0.90
     Jefus
    0.90
     houſe
    0.90
     pleaſure
    0.88
    Activations Density 3.351%

    No Known Activations