© 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. 7004
    Prev
    Next
    INDEX
    Explanations

    instances of someone trying to do something

    oai_token-act-pair · gemini-2.0-flash

    try

    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
    MLLoader
    -0.76
     AssemblyCompany
    -0.76
    يكب
    -0.73
    PerformLayout
    -0.71
    GEBURTSDATUM
    -0.70
    SourceChecksum
    -0.69
     AssemblyTitle
    -0.69
    tagHelperRunner
    -0.69
    //
    -0.67
    AddTagHelper
    -0.66
    POSITIVE LOGITS
     to
    0.69
    utton
    0.52
     their
    0.50
     its
    0.48
     it
    0.47
     her
    0.46
     your
    0.44
     словарь
    0.43
     this
    0.42
    eral
    0.41
    Activations Density 6.194%

    No Known Activations