© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8745
    Prev
    Next
    INDEX
    Explanations

    scientific prose describing galaxies and star formation

    oai_token-act-pair · gemini-2.0-flash

    astronomy texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     itſelf
    -0.59
     ſever
    -0.54
     mohair
    -0.54
     nhàng
    -0.53
    Havolalar
    -0.53
    adaptiveStyles
    -0.52
    SuppressLint
    -0.52
    InitVars
    -0.52
     UnityEditor
    -0.51
    spreis
    -0.50
    POSITIVE LOGITS
    ArgsConstructor
    0.58
    
    0.55
    PerformLayout
    0.55
    phazard
    0.55
     đỉnh
    0.52
    calaureate
    0.49
    quois
    0.49
    typedef
    0.49
     Trap
    0.48
    __()
    0.48
    Activations Density 1.368%

    No Known Activations