© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4178
    Prev
    Next
    INDEX
    Explanations

    text related to housing programs and legal restrictions

    oai_token-act-pair · gemini-2.0-flash

    teachers

    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
    WriteBarrier
    -0.73
    addCriterion
    -0.57
    MessageTagHelper
    -0.54
    ↹
    -0.52
    gridColumn
    -0.49
     económicas
    -0.49
     samfun
    -0.48
     AllAfrica
    -0.48
     onAnimation
    -0.47
    buttonBar
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.80
     teachers
    0.79
     Teachers
    0.69
     teacher
    0.69
    Teachers
    0.68
    teachers
    0.66
    httphttps
    0.64
     Teacher
    0.58
     Belvedere
    0.57
     middle
    0.56
    Activations Density 2.296%

    No Known Activations