© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12493
    Prev
    Next
    INDEX
    Explanations

    US state abbreviations

    oai_token-act-pair · 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
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.67
    ”.
    -0.55
     "
    -0.52
    <eos>
    -0.50
    ”
    -0.48
     EconPapers
    -0.48
     con
    -0.48
     kon
    -0.48
     di
    -0.47
     fra
    -0.45
    POSITIVE LOGITS
     MainAxisSize
    1.15
    arakhand
    0.94
     Efq
    0.93
     NUKAT
    0.90
    UnusedPrivate
    0.90
    хьтан
    0.82
     INTERESAR
    0.82
     Monfieur
    0.81
    reszcie
    0.80
    NESSEE
    0.79
    Activations Density 0.543%

    No Known Activations