© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11842
    Prev
    Next
    INDEX
    Explanations

    the contraction "don't"

    oai_token-act-pair · gemini-2.0-flash

    "don't" or "t"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     vectorielle
    -0.77
     vectorielles
    -0.77
     tfsi
    -0.71
     zoude
    -0.69
     vektör
    -0.69
     oock
    -0.68
     Mahomet
    -0.68
     صوتيه
    -0.65
     hänen
    -0.65
     ſche
    -0.65
    POSITIVE LOGITS
     you
    0.78
     be
    0.71
    はじめに
    0.54
    richTextPanel
    0.49
     des
    0.48
    des
    0.47
     You
    0.47
     act
    0.45
     snippetHide
    0.45
     Star
    0.45
    Activations Density 2.621%

    No Known Activations