© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8487
    Prev
    Next
    INDEX
    Explanations

    the word "rule" and words/phrases appearing close to it

    oai_token-act-pair · gemini-2.0-flash

    terms related to rules or regulations

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

    rule

    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
    Not in Any Lists

    No Comments

    Negative Logits
     murale
    -0.55
     AppCompatTheme
    -0.52
    ysing
    -0.50
    lež
    -0.49
    ếng
    -0.47
    urgi
    -0.47
    anueva
    -0.47
     souls
    -0.46
    мыш
    -0.45
     fee
    -0.45
    POSITIVE LOGITS
    djangoproject
    0.70
    StoryboardSegue
    0.61
    contentLoaded
    0.60
    QMetaType
    0.59
    Географиясе
    0.57
     nahilalakip
    0.54
     utafitiHapana
    0.52
    oredCriteria
    0.51
    ponses
    0.51
    MigrationBuilder
    0.50
    Activations Density 7.504%

    No Known Activations