© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3969
    Prev
    Next
    INDEX
    Explanations

    words that denote causality or results

    oai_token-act-pair · gemini-2.0-flash

    conjunctions

    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
     plaît
    -0.50
     doInBackground
    -0.49
     cherchez
    -0.46
     bagus
    -0.46
     baga
    -0.44
     couverts
    -0.44
     grievous
    -0.43
    rovna
    -0.43
     lanjut
    -0.43
    浑
    -0.43
    POSITIVE LOGITS
    tanleria
    0.77
    rungsseite
    0.76
     EconPapers
    0.75
    SequentialGroup
    0.75
    tagext
    0.71
    awtextra
    0.69
    Personendaten
    0.68
    migrationBuilder
    0.67
    ArrowToggle
    0.65
    billon
    0.65
    Activations Density 1.867%

    No Known Activations