© 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. 5633
    Prev
    Next
    INDEX
    Explanations

    content related to sports scores and categories

    oai_token-act-pair · gemini-2.0-flash

    tables of numeric data

    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
     Ro
    -0.59
     Al
    -0.53
     $
    -0.52
     Y
    -0.52
     charge
    -0.51
     делу
    -0.51
     Ay
    -0.51
    erta
    -0.50
     Ve
    -0.50
     Ly
    -0.49
    POSITIVE LOGITS
     becauſe
    0.78
     itſelf
    0.77
     myſelf
    0.76
     Majefty
    0.74
     Theſe
    0.73
    الحياه
    0.73
    ſelf
    0.72
    ſelves
    0.71
     crdi
    0.69
     uſe
    0.67
    Activations Density 7.571%

    No Known Activations