© 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. 5771
    Prev
    Next
    INDEX
    Explanations

    seemingly random punctuation, numbers, and some words in film reviews

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     given
    -0.66
     Italijanski
    -0.65
    ruptedException
    -0.63
     GIVEN
    -0.59
     stdClass
    -0.58
     but
    -0.58
    PyExc
    -0.57
     due
    -0.54
    OrNull
    -0.54
     TabLayout
    -0.54
    POSITIVE LOGITS
    ImageContext
    0.69
    few
    0.67
     Few
    0.63
     few
    0.63
    Few
    0.62
     Inscrivez
    0.59
     flesta
    0.57
     šķ
    0.56
     étrangers
    0.55
     része
    0.55
    Activations Density 2.220%

    No Known Activations