© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16202
    Prev
    Next
    INDEX
    Explanations

    words indicating possibility or conditionality

    oai_token-act-pair · gemini-2.0-flash

    possibility/futurity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     would
    -1.09
     could
    -0.98
     can
    -0.92
     was
    -0.86
     will
    -0.85
     is
    -0.84
     might
    -0.82
     cannot
    -0.75
     has
    -0.73
     should
    -0.69
    POSITIVE LOGITS
     beſt
    0.82
     ſeveral
    0.77
    Autoritní
    0.76
     reaſon
    0.73
     perſon
    0.72
     ſtate
    0.72
     faſt
    0.72
     preſent
    0.72
     ſuch
    0.71
     laſt
    0.71
    Activations Density 1.700%

    No Known Activations