© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10278
    Prev
    Next
    INDEX
    Explanations

    colons often surrounded by words related to code

    oai_token-act-pair · gemini-2.0-flash

    Code and API context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     out
    -0.97
     Out
    -0.68
     BoxFit
    -0.63
    jelent
    -0.59
    Out
    -0.58
    AutoScaleMode
    -0.57
    naut
    -0.54
    出的
    -0.53
    BoxShadow
    -0.53
     consultato
    -0.52
    POSITIVE LOGITS
     المعيارى
    0.66
    
    0.64
     disambiguazione
    0.60
    verwijspagina
    0.56
     Deposition
    0.56
    jubljana
    0.56
    UnusedPrivate
    0.52
     kie
    0.50
    __.__
    0.50
    альных
    0.50
    Activations Density 2.228%

    No Known Activations