© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2934
    Prev
    Next
    INDEX
    Explanations

    the number "3" and "3D"

    oai_token-act-pair · gemini-2.0-flash

    three

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Three
    -0.84
     ostavi
    -0.79
     three
    -0.74
    ]--;
    -0.72
     THREE
    -0.72
    ３
    -0.69
    三
    -0.69
    THREE
    -0.66
     خارجية
    -0.66
    Three
    -0.65
    POSITIVE LOGITS
    D
    0.69
     D
    0.60
    DM
    0.50
    d
    0.48
     d
    0.46
     DM
    0.46
     डी
    0.46
    DC
    0.46
    dc
    0.45
    DP
    0.44
    Activations Density 1.583%

    No Known Activations