© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14998
    Prev
    Next
    INDEX
    Explanations

    location names and other capitalized terms related to religion, royalty, or geography

    oai_token-act-pair · gemini-2.0-flash

    Religion and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Saint
    -0.69
     St
    -0.66
    St
    -0.66
    Saint
    -0.66
     st
    -0.64
     saint
    -0.57
    SAINT
    -0.52
    San
    -0.51
     SAINT
    -0.51
     San
    -0.50
    POSITIVE LOGITS
    AndroidJUnit
    0.90
    ParallelGroup
    0.84
    tvguidetime
    0.81
    มาะ
    0.79
    PerformLayout
    0.76
     TestBed
    0.75
     kasarigan
    0.75
    šinou
    0.72
    المناصب
    0.70
    TintMode
    0.69
    Activations Density 46.727%

    No Known Activations