© 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. 13681
    Prev
    Next
    INDEX
    Explanations

    leading whitespace and numbers within scientific papers

    oai_token-act-pair · gemini-2.0-flash

    neuroscience research

    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
    ölkerung
    -0.62
    Admission
    -0.60
     admission
    -0.59
     الحره
    -0.59
     Admission
    -0.52
     A
    -0.52
    endphp
    -0.50
    edad
    -0.50
    umab
    -0.49
    bewerken
    -0.48
    POSITIVE LOGITS
     juſ
    0.77
     ſte
    0.75
     itſelf
    0.75
     pleaſure
    0.75
     ſtate
    0.72
     raiſ
    0.72
     myſelf
    0.72
    setVerticalGroup
    0.71
     deſt
    0.69
     himſelf
    0.68
    Activations Density 0.877%

    No Known Activations