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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12533
    Prev
    Next
    INDEX
    Explanations

    mentions of software or information releases

    oai_token-act-pair · gemini-2.0-flash

    release

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     release
    -2.95
     released
    -2.64
     Release
    -2.63
    release
    -2.61
    Release
    -2.50
     releases
    -2.41
     releasing
    -2.38
    released
    -2.23
     RELEASE
    -2.23
     Released
    -2.22
    POSITIVE LOGITS
    brainly
    0.63
    Understood
    0.52
    Биография
    0.52
     المعيارى
    0.52
     bati
    0.50
    Rptr
    0.50
     baton
    0.50
     الحره
    0.50
    Hauptartikel
    0.48
     Swin
    0.48
    Activations Density 5.391%

    No Known Activations