© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2369
    Prev
    Next
    INDEX
    Explanations

    words related to outdoor activities, with emphasis on bringing things and also the definite article "a"

    oai_token-act-pair · gemini-2.0-flash

    packing for trips

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     auguri
    -0.51
    SharedDtor
    -0.50
    tagHelperRunner
    -0.49
    nocache
    -0.47
    不成
    -0.46
    ografija
    -0.46
    MoveNext
    -0.46
    不住
    -0.44
    డు
    -0.44
     ngoại
    -0.43
    POSITIVE LOGITS
    WebVitals
    0.75
     onCancelled
    0.75
     MotionEvent
    0.66
     Roskov
    0.63
    openqa
    0.63
    complexContent
    0.59
     jsPsych
    0.58
    phosa
    0.58
     незавершена
    0.57
    intellij
    0.56
    Activations Density 5.059%

    No Known Activations