© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3114
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of chemical and medical laboratory procedures

    oai_token-act-pair · gemini-2.0-flash

    Scientific research

    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
     debate
    -0.68
     discussion
    -0.64
     controversy
    -0.62
     debates
    -0.60
     scholarship
    -0.60
     consensus
    -0.59
     opinion
    -0.58
    debate
    -0.58
     knowledge
    -0.57
     statistics
    -0.57
    POSITIVE LOGITS
    oflavin
    0.52
     MainAxisSize
    0.44
     Cellulose
    0.44
    oprene
    0.44
     Soda
    0.43
     castor
    0.43
     Gypsum
    0.43
     coated
    0.43
    eradish
    0.43
     glycol
    0.42
    Activations Density 28.563%

    No Known Activations