© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9548
    Prev
    Next
    INDEX
    Explanations

    words related to legal or official documents along with some medical terms.

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     referring
    -0.75
     refer
    -0.70
     referred
    -0.66
    Refer
    -0.64
     refers
    -0.63
    refer
    -0.57
     Referring
    -0.56
     Refer
    -0.55
    évaluateur
    -0.53
    Referring
    -0.52
    POSITIVE LOGITS
    expandindo
    0.71
     forState
    0.63
    findpost
    0.61
    ритори
    0.58
    ülé
    0.55
    Aktualisiert
    0.54
    mouseleave
    0.54
    ایج
    0.54
    tvguidetime
    0.54
     Libre
    0.53
    Activations Density 15.930%

    No Known Activations