© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14222
    Prev
    Next
    INDEX
    Explanations

    mathematical, physics, or computer science jargon from research papers

    oai_token-act-pair · gemini-2.0-flash

    corresponding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     فيها
    -0.55
    íslu
    -0.54
    ConnectionState
    -0.54
     ErrIntOverflow
    -0.53
     bascul
    -0.51
    yntaxException
    -0.50
     préférence
    -0.50
    malade
    -0.50
    nofollow
    -0.49
     pouvaient
    -0.49
    POSITIVE LOGITS
    CreateMap
    0.63
    SourceChecksum
    0.54
     mergeFrom
    0.52
    EndTag
    0.49
     Dess
    0.49
     שוליים
    0.49
    NUMX
    0.47
     aca
    0.46
    IDA
    0.45
     ITIS
    0.45
    Activations Density 2.160%

    No Known Activations