© 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. 3810
    Prev
    Next
    INDEX
    Explanations

    the word "implications" and words or short phrases that are often associated with it

    oai_token-act-pair · gemini-2.0-flash

    implications

    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
    o
    -1.05
    i
    -0.88
    a
    -0.79
    k
    -0.76
    y
    -0.67
    ه
    -0.66
    li
    -0.66
    e
    -0.65
    ي
    -0.65
    er
    -0.64
    POSITIVE LOGITS
     ainfi
    1.09
    NUMX
    1.08
    $.
    1.05
     craindre
    1.03
     déclar
    0.98
    
    0.95
    )";
    0.93
    etheless
    0.91
     étoient
    0.90
    seamnă
    0.90
    Activations Density 2.379%

    No Known Activations