© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15367
    Prev
    Next
    INDEX
    Explanations

    questions and questioning statements

    oai_token-act-pair · gemini-2.0-flash

    How

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     How
    -0.63
    How
    -0.59
     Many
    -0.57
     how
    -0.55
     C
    -0.51
     to
    -0.50
    Many
    -0.49
     Man
    -0.48
     What
    -0.47
    What
    -0.46
    POSITIVE LOGITS
     leſs
    0.82
    InjectAttribute
    0.82
     ſmall
    0.81
     neceffary
    0.77
     reaſon
    0.77
     Majefty
    0.76
     theſe
    0.75
     Monfieur
    0.75
     neceſſ
    0.75
     defaultstate
    0.74
    Activations Density 2.028%

    No Known Activations