© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10173
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs like "to have" and related contractions.

    oai_token-act-pair · gemini-2.0-flash

    past participles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     myſelf
    -1.16
     Jefus
    -0.99
     perfons
    -0.96
     Majefty
    -0.95
     themſelves
    -0.92
     Efq
    -0.90
     himſelf
    -0.90
     Theſe
    -0.90
     Anſ
    -0.89
     itſelf
    -0.88
    POSITIVE LOGITS
     gone
    0.65
     fallen
    0.57
     come
    0.54
    Fallen
    0.52
     risen
    0.50
     Gone
    0.50
     GONE
    0.49
     gewonnen
    0.49
     broken
    0.49
     arisen
    0.48
    Activations Density 2.768%

    No Known Activations