© 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. 2648
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terms, particularly in the life sciences.

    oai_token-act-pair · gemini-2.0-flash

    Variety

    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
     ſmall
    -0.59
    NOPQRST
    -0.56
     pleaſure
    -0.54
     popularity
    -0.53
     despe
    -0.52
     Estudi
    -0.52
    !")
    -0.52
     Matéri
    -0.52
    igshid
    -0.52
    کاری
    -0.51
    POSITIVE LOGITS
    onAttach
    0.72
     <=",
    0.67
     فريبيس
    0.64
    rungsseite
    0.59
     XCTest
    0.52
    PerformLayout
    0.49
    adaptiveStyles
    0.49
    FormBorderStyle
    0.49
     externes
    0.49
    nonatomic
    0.49
    Activations Density 22.734%

    No Known Activations