© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13682
    Prev
    Next
    INDEX
    Explanations

    a mix of terms from medicine, physics, and chemistry

    oai_token-act-pair · gemini-2.0-flash

    scientific/medical issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     mauvaises
    -0.49
    væ
    -0.47
     ๆ
    -0.44
     phénomènes
    -0.44
     secteurs
    -0.44
     mauvaise
    -0.43
    ájá
    -0.43
     kerugian
    -0.42
     considér
    -0.42
    cyklo
    -0.42
    POSITIVE LOGITS
    رشف
    0.73
    IBOutlet
    0.69
    DebuggerNonUser
    0.69
    DeleteBehavior
    0.67
     beginnetje
    0.64
     doInBackground
    0.64
    Rhestr
    0.61
     rheumat
    0.60
    astéroïdes
    0.59
    fjspx
    0.58
    Activations Density 3.046%

    No Known Activations