© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13811
    Prev
    Next
    INDEX
    Explanations

    words and symbols that are mostly used in scientific documents

    oai_token-act-pair · gemini-2.0-flash

    horizon and cooling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Method
    -0.59
    prechen
    -0.56
     concessions
    -0.53
     mustered
    -0.52
    (&:
    -0.52
    anho
    -0.51
    Eh
    -0.49
     EH
    -0.47
     depositions
    -0.47
     AEG
    -0.46
    POSITIVE LOGITS
     surla
    0.82
     ComVisible
    0.68
    帖最后由
    0.66
    brainly
    0.66
    expandindo
    0.63
    WriteBarrier
    0.62
    oa̍t
    0.62
     ainfi
    0.62
    EndContext
    0.61
    الحياه
    0.61
    Activations Density 10.902%

    No Known Activations