© 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. 15273
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly unrelated words

    oai_token-act-pair · 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
     CreateTagHelper
    -0.96
    はじめに
    -0.54
    prnewswire
    -0.53
    prehensive
    -0.52
    
    -0.51
    WithIOException
    -0.50
    EditorBrowsable
    -0.49
     Exactos
    -0.47
    actionMode
    -0.46
    ══
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    0.62
     auffi
    0.60
    цездатний
    0.58
     наоборот
    0.58
    則是
    0.57
     poffible
    0.57
     counterparts
    0.56
    principalColumn
    0.55
    Spoljašnje
    0.54
    Välislingid
    0.54
    Activations Density 1.434%

    No Known Activations