© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11706
    Prev
    Next
    INDEX
    Explanations

    the word "indirect" when discussing research and medical testing methods

    oai_token-act-pair · gemini-2.0-flash

    indirect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     siguran
    -0.65
    x
    -0.64
    SA
    -0.61
    sk
    -0.60
    ↵↵
    -0.59
    S
    -0.58
    c
    -0.57
    A
    -0.57
    How
    -0.56
     noastre
    -0.56
    POSITIVE LOGITS
    MemoryWarning
    1.48
     autorytatywna
    1.41
     مشين
    1.30
     CreateTagHelper
    1.29
    abestanden
    1.29
     שוליים
    1.28
    PerformLayout
    1.23
     Мексичка
    1.20
     فريبيس
    1.18
    extAlignment
    1.16
    Activations Density 0.861%

    No Known Activations