© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4821
    Prev
    Next
    INDEX
    Explanations

    Lithuanian words or names

    oai_token-act-pair · gemini-2.0-flash

    Mixed code and language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     one
    -0.47
    l
    -0.42
    e
    -0.41
     ever
    -0.40
    atus
    -0.38
     
    -0.37
    v
    -0.35
    ư
    -0.35
     again
    -0.34
    gee
    -0.34
    POSITIVE LOGITS
    WriteBarrier
    1.01
     Theſe
    0.94
     itſelf
    0.92
    ſelves
    0.91
    MLLoader
    0.90
     myſelf
    0.90
     becauſe
    0.88
    rungsseite
    0.87
    WriteLiteral
    0.87
     auffi
    0.85
    Activations Density 0.100%

    No Known Activations