© 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. 4606
    Prev
    Next
    INDEX
    Explanations

    phrases related to understanding, confusion, and being unable to understand

    oai_token-act-pair · gemini-2.0-flash

    under

    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
    IntoConstraints
    -0.67
     Efq
    -0.67
     betweenstory
    -0.66
    SourceChecksum
    -0.63
     useStyles
    -0.59
     myſelf
    -0.59
    rawDesc
    -0.58
    argout
    -0.57
    toBeTruthy
    -0.55
     tfsi
    -0.55
    POSITIVE LOGITS
     UNDER
    1.54
     under
    1.54
    UNDER
    1.48
    under
    1.44
     Under
    1.41
    Under
    1.34
     unter
    1.12
     unders
    1.05
     und
    1.02
     unde
    0.93
    Activations Density 1.013%

    No Known Activations