© 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. 3407
    Prev
    Next
    INDEX
    Explanations

    sentences describing biological processes at a molecular level, particularly those involving enzymes, cells, and polynucleotides

    oai_token-act-pair · gemini-2.0-flash

    immune system/enzymes

    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
     unit
    -1.28
     Unit
    -1.25
    unit
    -1.16
    Unit
    -1.16
     UNIT
    -1.12
    UNIT
    -1.08
     cell
    -0.98
    ########.
    -0.88
     Cell
    -0.88
     enzyme
    -0.83
    POSITIVE LOGITS
    landt
    0.52
    ressee
    0.50
    ựng
    0.49
    
    0.49
     catalog
    0.48
    supset
    0.47
    posedge
    0.46
     catalogue
    0.46
     barba
    0.46
    onucle
    0.44
    Activations Density 5.522%

    No Known Activations