© 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. 4662
    Prev
    Next
    INDEX
    Explanations

    complicated multi-clause sentences that contain the words "are" "were" or "was"

    oai_token-act-pair · gemini-2.0-flash

    turn

    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
    CodedInputStream
    -0.60
    ::_('
    -0.57
    MemoryWarning
    -0.57
    aarrggbb
    -0.55
    WillAppear
    -0.54
    جوايز
    -0.54
    ()]
    -0.52
    IntoConstraints
    -0.52
    libft
    -0.52
    (":");
    -0.52
    POSITIVE LOGITS
     turned
    0.78
    turned
    0.68
     turns
    0.66
    Turned
    0.62
     Turned
    0.62
     Turns
    0.61
    Turns
    0.61
     تضيفلها
    0.57
     turn
    0.57
     TURN
    0.54
    Activations Density 1.956%

    No Known Activations