© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14767
    Prev
    Next
    INDEX
    Explanations

    the word "it" and the verb "to be".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    mise
    -0.57
    drawSprites
    -0.54
    homonymie
    -0.52
    stddef
    -0.52
    ніципа
    -0.49
    ğum
    -0.48
     Complexes
    -0.47
    elesaikan
    -0.47
     OFFICES
    -0.47
     unmute
    -0.46
    POSITIVE LOGITS
     took
    1.10
    Took
    1.10
     Took
    1.05
    took
    1.02
    Taken
    0.91
     taken
    0.88
     Taken
    0.87
    Taking
    0.85
    taken
    0.82
     Taking
    0.79
    Activations Density 2.127%

    No Known Activations