© 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. 15611
    Prev
    Next
    INDEX
    Explanations

    words preceding instances of 'the', directional words, and words related to reporting or fixing something.

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terminology

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

    streets roads

    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
    Fazit
    -0.56
    JspWriter
    -0.54
    FTFY
    -0.54
    Einzelnachweise
    -0.52
    getColumnIndex
    -0.52
    labelledby
    -0.49
     invertebrates
    -0.49
     ARS
    -0.49
     esser
    -0.49
    Externe
    -0.49
    POSITIVE LOGITS
    #+#
    0.68
     الاطلاع
    0.68
    rungsseite
    0.58
    setViewportView
    0.51
    SequentialGroup
    0.49
     side
    0.47
     publiés
    0.46
    èlement
    0.45
     totalSupply
    0.45
    +#+#
    0.44
    Activations Density 1.077%

    No Known Activations