© 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. 1358
    Prev
    Next
    INDEX
    Explanations

    legal jargon related to court proceedings and documents

    oai_token-act-pair · gemini-2.0-flash

    official 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
     offer
    -0.46
     offered
    -0.44
     "
    -0.43
     '
    -0.42
    olingo
    -0.40
     “
    -0.40
     e
    -0.40
     -
    -0.39
    offer
    -0.39
     ofrec
    -0.39
    POSITIVE LOGITS
     ſeveral
    1.04
     ſtate
    1.04
     pleaſure
    1.04
     ſche
    1.03
     Reſ
    1.02
     Jefus
    1.01
    ſelves
    1.01
    +#+#
    0.99
     Majefty
    0.99
     getItemId
    0.98
    Activations Density 2.423%

    No Known Activations