© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1590
    Prev
    Next
    INDEX
    Explanations

    the word "left" followed by a preposition such as "out" or "over"

    oai_token-act-pair · gemini-2.0-flash

    words regarding exclusion or omission

    np_token-act-pair-logits · gpt-4o-mini

    something "left"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    WireFormat
    -0.77
    tagHelperRunner
    -0.72
    ValueStyle
    -0.70
    SerializedSize
    -0.69
    IndentedString
    -0.67
    UIControlState
    -0.60
    PreferredItem
    -0.59
    تقاوى
    -0.59
    GraphicsUnit
    -0.58
    usermodel
    -0.56
    POSITIVE LOGITS
     Bourgoin
    0.56
     souple
    0.53
     malheure
    0.52
    徊
    0.52
     igång
    0.52
     perpétu
    0.51
    adura
    0.50
     lệ
    0.49
    îné
    0.49
    ckeye
    0.48
    Activations Density 1.801%

    No Known Activations