© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3118
    Prev
    Next
    INDEX
    Explanations

    code snippets with returns and validation

    oai_token-act-pair · 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
    
    -0.84
     مشين
    -0.81
     esternos
    -0.75
     snippetHide
    -0.75
    dafx
    -0.75
    tagHelperRunner
    -0.73
    ValueStyle
    -0.73
    #+#
    -0.72
     continúas
    -0.71
     nahilalakip
    -0.70
    POSITIVE LOGITS
     Beecher
    0.48
     onCancelled
    0.45
    messageInfo
    0.45
    !="")
    0.44
     asupra
    0.43
    地说道
    0.43
    ']").
    0.43
    kkor
    0.42
    FormItem
    0.40
    🥣
    0.40
    Activations Density 0.933%

    No Known Activations