© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8640
    Prev
    Next
    INDEX
    Explanations

    statistics or information derived from polls or surveys

    oai_token-act-pair · gemini-2.0-flash

    survey results

    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
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.81
     nonatomic
    -0.79
     AssemblyTitle
    -0.78
     GlobalKey
    -0.77
    MemoryWarning
    -0.73
     ujednoznacz
    -0.69
     disambiguazione
    -0.68
     StatelessWidget
    -0.67
    RectangleBorder
    -0.66
    rungsseite
    -0.64
    POSITIVE LOGITS
     say
    0.73
     said
    0.65
     answer
    0.63
     says
    0.63
     répondu
    0.59
     answers
    0.56
     EconPapers
    0.56
     point
    0.55
     were
    0.53
     saying
    0.53
    Activations Density 4.284%

    No Known Activations