© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8934
    Prev
    Next
    INDEX
    Explanations

    technical language from biochemistry papers

    oai_token-act-pair · gemini-2.0-flash

    scientific language

    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
     Oxid
    -1.12
     oxid
    -1.05
     Oxidation
    -1.05
    Oxid
    -1.04
     oxidizing
    -1.04
     oxidized
    -1.02
     oxidation
    -1.01
    oxid
    -1.00
     oxidative
    -0.96
    oxidants
    -0.94
    POSITIVE LOGITS
     purpure
    0.46
     jätte
    0.45
    lių
    0.44
    Wa
    0.44
    Topic
    0.44
    super
    0.43
     væ
    0.43
     Giant
    0.43
     bū
    0.42
     túl
    0.42
    Activations Density 1.625%

    No Known Activations