© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2055
    Prev
    Next
    INDEX
    Explanations

    text from legal and mathematical documents

    oai_token-act-pair · gemini-2.0-flash

    legal, technical definitions

    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
    Datuak
    -0.59
     Schengen
    -0.59
    erapeu
    -0.54
     Audiodateien
    -0.53
    toPromise
    -0.53
     smtplib
    -0.53
    sunflower
    -0.52
    RegistryLite
    -0.52
     GenerationType
    -0.52
     Benzema
    -0.51
    POSITIVE LOGITS
    addCriterion
    0.71
    DeleteBehavior
    0.50
    aarrggbb
    0.48
    br
    0.47
     particular
    0.46
    WithIOException
    0.45
    ئ
    0.45
    entierung
    0.44
    ßten
    0.44
    verture
    0.44
    Activations Density 10.257%

    No Known Activations