© 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. 13070
    Prev
    Next
    INDEX
    Explanations

    code and technical documents, particularly mentions of biofuel, biotech, and molecular biology

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific documentation

    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
     bio
    -3.16
     Bio
    -3.00
    Bio
    -2.88
    bio
    -2.80
     BIO
    -2.45
    BIO
    -2.42
     био
    -2.34
     biological
    -2.20
     bios
    -2.16
     Biological
    -2.06
    POSITIVE LOGITS
    DataAnnotations
    0.60
    migrationBuilder
    0.53
    Према
    0.51
    блиоте
    0.49
    stdc
    0.47
    Населення
    0.45
    encodeWith
    0.44
    gcf
    0.44
    بوابة
    0.44
     foramen
    0.44
    Activations Density 5.285%

    No Known Activations