© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2413
    Prev
    Next
    INDEX
    Explanations

    text that is gibberish or a foreign language

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Normdatei
    -0.62
    skjaer
    -0.54
    ptonshire
    -0.52
    thâu
    -0.52
    UserScript
    -0.51
    riwal
    -0.51
    batore
    -0.50
    doria
    -0.50
     TextAppearance
    -0.49
    opardy
    -0.49
    POSITIVE LOGITS
     zijne
    0.52
     orizz
    0.52
     enfans
    0.51
     églises
    0.49
     prêtres
    0.49
    ং
    0.49
     insectes
    0.48
     chré
    0.47
     dégâts
    0.47
     gouttes
    0.47
    Activations Density 1.503%

    No Known Activations