© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7473
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to scientific and engineering fields

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     prenant
    -0.66
     realising
    -0.62
    seeing
    -0.62
     ThemeData
    -0.61
     realizing
    -0.60
     hitting
    -0.60
     textStatus
    -0.60
    creating
    -0.59
     Creating
    -0.59
    TestingModule
    -0.59
    POSITIVE LOGITS
    cede
    0.60
     operate
    0.58
    curity
    0.57
    ceed
    0.56
     Operate
    0.55
    CUSS
    0.54
    Operate
    0.53
    scry
    0.53
    martre
    0.53
    ibrate
    0.53
    Activations Density 12.687%

    No Known Activations