© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14297
    Prev
    Next
    INDEX
    Explanations

    the word "touch", sometimes combined with words like "dollars"

    oai_token-act-pair · gemini-2.0-flash

    touch

    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
     touch
    -0.70
     Touch
    -0.66
    touch
    -0.66
    Touch
    -0.62
     touches
    -0.53
     температуре
    -0.52
     TOUCH
    -0.52
    PasswordEncoder
    -0.51
    čkou
    -0.50
    ếu
    -0.49
    POSITIVE LOGITS
     استنادى
    0.88
    :✨
    0.88
    EDEFAULT
    0.84
     pinulongan
    0.81
    Билгалдахарш
    0.80
     يتيمه
    0.76
    AndEndTag
    0.74
    Portale
    0.72
    JspWriter
    0.72
     الحره
    0.72
    Activations Density 1.126%

    No Known Activations