© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6291
    Prev
    Next
    INDEX
    Explanations

    the letter "U" followed by a single-digit number

    oai_token-act-pair · gemini-2.0-flash

    U

    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
     Chwiliwch
    -0.73
    AnimationsModule
    -0.59
     trì
    -0.53
    oa̍t
    -0.53
     horns
    -0.52
     AssemblyCulture
    -0.51
    AutoScaleMode
    -0.50
    xically
    -0.50
    setVerticalGroup
    -0.50
    ALT
    -0.50
    POSITIVE LOGITS
     ArrayAdapter
    0.52
    colgroup
    0.52
    EndContext
    0.49
    oq
    0.48
    decoded
    0.48
    yyj
    0.47
    InputTagHelper
    0.46
    Coconut
    0.44
    Hills
    0.43
    waitKey
    0.42
    Activations Density 0.938%

    No Known Activations