© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2478
    Prev
    Next
    INDEX
    Explanations

    text that contains numbers and is formatted like a Wikipedia entry

    oai_token-act-pair · gemini-2.0-flash

    Higher education

    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
    StoryboardSegue
    -0.73
     distanciation
    -0.66
     doInBackground
    -0.66
     للمعارف
    -0.64
    RectangleBorder
    -0.63
     समीक्षाएं
    -0.63
    دانشنامهٔ
    -0.62
    PMailer
    -0.62
    IBinder
    -0.61
    новниш
    -0.60
    POSITIVE LOGITS
     cercanos
    0.49
    pagnols
    0.49
     administrativos
    0.48
     universitarios
    0.46
    ثيل
    0.45
     académico
    0.42
     deportivos
    0.42
    timewa
    0.41
     înc
    0.41
    itário
    0.40
    Activations Density 15.728%

    No Known Activations