© 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. 9998
    Prev
    Next
    INDEX
    Explanations

    image file names and website URLs

    oai_token-act-pair · gemini-2.0-flash

    png

    np_max-act · gemini-2.0-flash

    png

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ,
    -0.66
     el
    -0.65
    ing
    -0.59
    el
    -0.59
    self
    -0.56
    al
    -0.52
    íně
    -0.52
     er
    -0.51
     actually
    -0.50
    tung
    -0.50
    POSITIVE LOGITS
    DockStyle
    1.23
    setVerticalGroup
    1.05
    posedge
    1.03
     виправивши
    1.03
     незавершена
    1.00
    IntoConstraints
    0.94
    ChildScrollView
    0.94
    adaptiveStyles
    0.93
     beginnetje
    0.91
    IUrlHelper
    0.90
    Activations Density 1.361%

    No Known Activations