© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 636
    Prev
    Next
    INDEX
    Explanations

    clauses that contain contrasting information

    oai_token-act-pair · gemini-2.0-flash

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    appui
    -0.41
    ragos
    -0.40
    !("{}",
    -0.38
     Forgot
    -0.38
    eleri
    -0.37
     aware
    -0.37
    Ă
    -0.37
    Ț
    -0.35
     locura
    -0.35
     Stopped
    -0.35
    POSITIVE LOGITS
    esModule
    0.86
    astify
    0.73
    GraphicsUnit
    0.70
    LookAnd
    0.69
    CppMethod
    0.69
    WireFormatLite
    0.67
    ftagPool
    0.67
     للمعارف
    0.67
    resave
    0.66
     الرياضيه
    0.65
    Activations Density 3.125%

    No Known Activations