© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4002
    Prev
    Next
    INDEX
    Explanations

    instances of leading teams or individuals

    oai_token-act-pair · gemini-2.0-flash

    lead

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     itſelf
    -0.97
     myſelf
    -0.89
    Geplaatst
    -0.85
    ſelves
    -0.85
     raiſ
    -0.85
     doubtnut
    -0.84
    WriteTagHelper
    -0.84
     Reſ
    -0.84
     ſta
    -0.84
    ſelf
    -0.83
    POSITIVE LOGITS
     L
    0.57
     Ron
    0.48
     av
    0.48
     te
    0.46
     T
    0.45
    ্ত
    0.45
     O
    0.44
     tom
    0.43
     con
    0.43
     an
    0.43
    Activations Density 8.593%

    No Known Activations