© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3954
    Prev
    Next
    INDEX
    Explanations

    text related to the acronym "NT", or "ec" with other letters, the suffix "ian", or the word "spread".

    oai_token-act-pair · gemini-2.0-flash

    Spread

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     spread
    -2.19
    spread
    -2.02
     Spread
    -1.91
     spreads
    -1.89
    Spread
    -1.88
     spreading
    -1.67
     Spreading
    -1.52
    spreading
    -1.36
     spreader
    -1.05
    pread
    -1.02
    POSITIVE LOGITS
    مصادر
    0.64
    SequentialGroup
    0.51
    Viki
    0.50
    ysh
    0.49
     ComVisible
    0.48
    aires
    0.48
    :+:
    0.48
    braucher
    0.48
    vited
    0.47
    atural
    0.47
    Activations Density 9.490%

    No Known Activations