© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14131
    Prev
    Next
    INDEX
    Explanations

    language from technical patents describing mechanical devices.

    oai_token-act-pair · gemini-2.0-flash

    Patent descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     فريبيس
    -0.53
     catena
    -0.51
    ChildScrollView
    -0.49
     ExecuteAsync
    -0.48
    ubility
    -0.47
    χεία
    -0.45
    intios
    -0.43
    éric
    -0.43
    InstrumentedTest
    -0.43
     disarm
    -0.43
    POSITIVE LOGITS
    存于互联网档案馆
    0.62
    xase
    0.60
    endaft
    0.55
    idoscope
    0.55
    kloped
    0.54
    styleType
    0.53
    pushFollow
    0.53
    enem
    0.53
     coö
    0.52
    ieteur
    0.52
    Activations Density 2.404%

    No Known Activations