© 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. 5948
    Prev
    Next
    INDEX
    Explanations

    the word "reason" and other words that relate to storytelling like "form" and "speaking".

    oai_token-act-pair · gemini-2.0-flash

    reason

    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
    <bos>
    -0.97
     Jefus
    -0.86
     moschino
    -0.82
     Cæsar
    -0.73
     Eocene
    -0.70
     whoſe
    -0.70
     Majefty
    -0.69
     hvid
    -0.68
     stiefel
    -0.68
     againſt
    -0.67
    POSITIVE LOGITS
     obviously
    1.02
     unfortunately
    0.94
    obviously
    0.90
    mittedly
    0.87
     therefore
    0.84
     obviamente
    0.82
     admittedly
    0.74
    Obviously
    0.74
     indeed
    0.73
    erdings
    0.73
    Activations Density 0.649%

    No Known Activations