© 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. 4529
    Prev
    Next
    INDEX
    Explanations

    the letters "J" or "Ref" by themselves

    oai_token-act-pair · gemini-2.0-flash

    ref

    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
     Efq
    -1.45
    expandindo
    -1.40
     EconPapers
    -1.35
     autorytatywna
    -1.35
    tvguidetime
    -1.32
     للمعارف
    -1.27
    SharedDtor
    -1.26
    RenderAtEndOf
    -1.24
    ^(@)
    -1.24
     дописавши
    -1.23
    POSITIVE LOGITS
    ↵
    0.97
    ↵↵
    0.94
    .
    0.85
    <eos>
    0.80
    I
    0.79
    T
    0.77
    S
    0.76
    1
    0.71
    ↵↵↵
    0.71
    an
    0.71
    Activations Density 1.099%

    No Known Activations