© 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. 6353
    Prev
    Next
    INDEX
    Explanations

    scientific language relating to physics and chemistry, particularly properties and materials

    oai_token-act-pair · gemini-2.0-flash

    proper

    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
     egens
    -0.74
     ModelExpression
    -0.73
    Xna
    -0.68
     attributes
    -0.65
    IsContent
    -0.65
    webElementXpaths
    -0.64
     Attributes
    -0.63
     Assets
    -0.61
    SharedCtor
    -0.60
    хьтан
    -0.60
    POSITIVE LOGITS
     proper
    2.33
    proper
    2.20
     Proper
    2.14
    Proper
    2.13
     PROPER
    1.82
     properly
    1.58
    properly
    1.55
     Properly
    1.36
     improper
    1.09
     prop
    1.05
    Activations Density 2.520%

    No Known Activations