© 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. 1809
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that are important to the text, but not necessarily semantically related

    oai_token-act-pair · gemini-2.0-flash

    programming syntax and tokens

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

    code/technical language

    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
    WithMany
    -0.80
     تضيفلها
    -0.65
    SequentialGroup
    -0.65
     فريبيس
    -0.61
    unhofer
    -0.61
     geografic
    -0.60
    AsUp
    -0.59
    MergeFrom
    -0.59
    AutoScaleMode
    -0.57
    MigrationBuilder
    -0.57
    POSITIVE LOGITS
     colspan
    0.56
     HasFactory
    0.53
    はじめに
    0.52
    --*/
    0.50
    \}\\
    0.50
    ();*/
    0.49
     STEIN
    0.48
    */)
    0.47
    })*/
    0.46
    Tembelea
    0.46
    Activations Density 6.630%

    No Known Activations